/ CHANGELOG.md
CHANGELOG.md
1 # Changelog 2 3 All notable changes to this project will be documented in this file. 4 5 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), 6 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). 7 8 ## [v4.1.6] - 2026-04-23 9 10 ### Added 11 - **Docker**: Add git to runtime dependencies in Dockerfile (69f7430) 12 - **Vuln Rules**: Add AIG vulnerability rules [2026-04-23] (#350) 13 - **Vuln Rules**: Detect exposed AI agent config files (claude_desktop_config.json, mcp.json, etc.) (#340) 14 - **Vuln Rules**: Add Trae IDE and CodeBuddy MCP config paths, extend .env key patterns 15 - **Data Sync**: Replace zip download with git clone, remove github_token dependency (#327) 16 - **Manual Updates**: Support manual updates to the latest jailbreak datasets, fingerprints, and vulnerability databases 17 - **Update API**: Merge update-status into update-data endpoint 18 19 ### Fixed 20 - **Vuln Rules**: Revert .env matcher to API key pattern matching 21 - **Vuln Rules**: Remove mcpServers field dependency, match on file format only 22 - **Vuln Rules**: Replace substring match with regex to reduce false positives 23 - **Update API**: Return status=1 when last sync failed 24 - **Update API**: Unify response format to {status, message, data} 25 - **Update API**: Remove request params, always sync main branch 26 - **Data Sync**: Harden update_api against CodeQL path-injection and command-injection alerts 27 - **Vuln Rules**: Update GHSA-8fmp-37rc-p5g7.yaml and OpenClaw versioning rule 28 29 ### Contributors 30 Special thanks to @feiyang666, @zhuque, @boyhack, @aigsec, @aig-doc-bot 31 32 --- 33 34 ## [v4.1.4] - 2026-04-17 35 36 ### Security 37 - **TLS**: Support HTTPS connections with self-signed/private CA certificates for model endpoints; add InsecureSkipVerify option (#306, closes #302) 38 39 ### Added 40 - **MCP Scan**: Add multi-turn red team attack module with TAP and Crescendo strategies (#299) 41 - **System API**: Add data auto-sync API (`POST /api/v1/system/update-data`, `GET /api/v1/system/update-status`) for syncing `data/` directory (#301) 42 - **Agent Scan API**: Support inline `agent_config` in agent scan API, make verify optional on save (#322) 43 - **CLI**: Support `--agent-config-file` for inline YAML agent scan config (aig-scanner v1.0.3) 44 - **Security Policy**: Add SECURITY.md with trust model and vulnerability disclosure policy 45 46 ### Fixed 47 - **Vulnerability Rules**: Fill empty rule fields and add new CVE rules 48 - **API**: Fix mcp_scan content field and add agent_scan API documentation 49 - **Docs**: Fix HTML block bold rendering in multilingual READMEs 50 - **Architecture**: Fix runtime path resolution for local deployments 51 52 ### Changed 53 - **Codebase**: Convert all Chinese comments and messages to English in api.go and knowledge2_api.go 54 - **Docs**: Expand Related Papers to 17 entries with 5 new 2026 papers; sync across all multilingual READMEs 55 - **Docs**: Add architecture evolution document covering v0.1/v2.6/v3.6.0 (#294) 56 - **Vulnerability Stats**: Update component vulnerability counts, add crewai/kubeai/lobehub entries (#291) 57 58 ### Contributors 59 Special thanks to @boyhack, @zhuque, @ac0d3r, @feiyang666, @rocie799, @aig-doc-bot 60 61 --- 62 63 ## [v4.1.3] - 2026-04-09 64 65 ### Fixed 66 - **Fingerprint**: Add version extractor to OpenClaw fingerprint for accurate version detection (#286) 67 - **MCP Scan**: Harden agent loop and path validation, clean up config (#282) 68 69 ### Changed 70 - **Vulnerability Rules**: Remove duplicate GHSA files already covered by CVE entries (OpenClaw dedup) 71 72 ### Documentation 73 - Add quick usage guide with concrete scan target examples (issue #281) 74 - Sync env.example context window vars, update install and test commands for MCP scan 75 - Fix README_JA quick guide missing sections and correct OpenClaw vuln count (474→451) 76 - Restructure and sync What's New sections across EN/ZH/JA READMEs 77 78 ### Contributors 79 Special thanks to @boyhack, @zhuque, @zznQ, @feiyang666, @juciepie, @aig-doc-bot 80 81 --- 82 83 ## [v4.1.2] - 2026-04-03 84 85 ### Fixed 86 - **Task Control**: Added support for stopping running tasks, allowing users to actively terminate scans in progress 87 - **AI Infra Scan**: Fixed a bug where the "No Model" option could not be selected in AI infrastructure scan task configuration, preventing users from creating model-free scan tasks 88 - **AI Infra Scan**: Fixed double-dot filename bug in scan file upload that caused certain filenames to be incorrectly rejected 89 - **AI Infra Scan**: Fixed concurrent goroutine hang in multi-IP scan scenarios, improving scan stability and task completion reliability 90 - **Agent Scan**: Hardened LLM error handling to prevent scan crashes on unexpected model responses 91 - **LLM Input**: Fixed inappropriate input text passed to LLM in certain scan scenarios 92 93 ### Added 94 - **Vulnerability Rules [2026-03-26]**: Added 15 new CVE rules covering n8n (×11), OpenClaw (×3), llama.cpp (×1) 95 - **Vulnerability Rules [2026-03-27]**: Added 29 new CVE rules covering BentoML (×1), Langflow (×2), OpenClaw (×26); added BentoML fingerprint 96 - **Vulnerability Rules [2026-03-30]**: Added 15 new CVE rules covering Langflow (×1), LibreChat (×4), LoLLMs (×1), MLflow (×1), OpenClaw (×8); added Wallos fingerprint 97 - **Coverage**: AI component vulnerability coverage expanded to **52 components / 1000+ CVEs** 98 99 ### Changed 100 - **Fingerprint Accuracy**: Aligned fingerprint `info.name` with vulnerability rule names for consistent detection matching 101 - **Documentation**: Updated AI infra scan component and CVE statistics in README 102 103 ### Contributors 104 Special thanks to @feiyang666, @Yang1k, @aigsec 105 106 --- 107 108 ## [v4.1.1] - 2026-03-25 109 110 ### Added 111 - **New Vulnerability Rules**: Added AIG rules batch [2026-03-25], expanding AI component vulnerability detection coverage 112 - **Fingerprint Enhancement**: Added correct new-api fingerprint matcher syntax (FOFA 100%) 113 114 ### Fixed 115 - **Security**: Mask token fields in GetTaskDetail response to prevent credential leakage (#226) 116 - **MCP Scan**: Fix missing imports and mcp_tool alias in mcp_tool module 117 - **Documentation**: Fix incorrect license name in README.md; fix MIT license reference in README_ZH Features section 118 119 ### Changed 120 - **CI**: Optimize yaml-lint workflow with Go cache and failure artifact upload 121 - **Docs**: Update README What's New section to reflect v4.1 features accurately 122 123 ### Contributors 124 Special thanks to @feiyang666, @zhuque, @aigsec 125 126 --- 127 128 ## [v4.1] - 2026-03-23 129 130 ### Added 131 - **New Scan Port**: Added port 18789 to the default AI infrastructure scan port list for broader AI component coverage 132 - **New Vulnerability Rules**: Added AIG Rules (2026-03-20 batch), continuously expanding the AI component vulnerability detection rule library 133 - **OpenClaw Vulnerability Database**: Added 281 new CVE/GHSA entries for OpenClaw components, covering a wide range of AI infrastructure security advisories 134 - **YAML CI/CD Validation**: Introduced automated YAML format validation pipeline via CSCD; triggered on PR and Push events to ensure rule compliance before merge 135 - **Task API Enhancement**: Improved taskapi lifecycle management and Agent Scan support 136 - **edgeone-clawscan Skill**: Added EdgeOne-based ClawScan security scanning Skill powered by Tencent Zhuque Lab AI-Infra-Guard 137 138 ### Changed 139 - **License Migration**: Migrated from MIT to Apache 2.0; added NOTICE file with attribution requirements 140 - **License Headers**: Added Apache 2.0 license headers to all `.go` and `.py` source files 141 142 ### Fixed 143 - **CodeQL Hardening**: Completed CodeQL path-injection remediation (Round 2), closing all related security alerts 144 - **Score Normalization**: Fixed severity case inconsistency in `CalcSecScore` and added support for Chinese severity levels (#178) 145 - **Agent Config Path Validation**: Fixed path injection risk in `readAgentConfigContent`, added input validation and boundary checks 146 - **Documentation Fixes**: Fixed ClawScan URL formatting, broken links, and other documentation errors 147 148 ### Docs 149 - Added AI coding assistant guideline files: CLAUDE.md, CODEBUDDY.md, AGENTS.md 150 - Updated README and README_ZH.md with v4.0 feature descriptions and capability overview 151 - Moved license section to bottom of README_ZH.md; fixed license filename reference to `LICENSE` 152 153 ### Changed (additional) 154 - Enforced open-source standards across README, CHANGELOG, NOTICE, and YAML CI configuration 155 156 ### Contributors 157 Special thanks to @zhuque, @boyhack, @Nicky, @rocie799, @aigsec 158 159 --- 160 161 ## [v4.0] - 2026-03-10 162 163 ### Added 164 - **Agent-Scan Framework**: Introduced a brand-new Agent-Scan scanning engine — a complete AI-powered autonomous agent security scanning framework 165 - Multi-agent architecture with specialized sub-agents: main agent, SSRF agent, config-scanner agent, vulnerability detector agent, agent security reviewer, and data leakage detection agent 166 - Full tool ecosystem including bash, file read/write, edit, grep, glob, ls, batch, thinking, todo, task, skill, MCP tool, dialogue, and finish actions 167 - Agent adapter system with support for multiple providers (Dify, Coze, etc.) with streaming response and connectivity testing 168 - Skill-based scanning capabilities: OWASP ASI compliance, authorization bypass detection, indirect injection detection, tool abuse detection, data leakage detection (with static & advanced prompt sets and LLM evaluator) 169 - Agent security review report generation with structured vulnerability assessment 170 - Scan pipeline with dialogue count tracking, tool usage statistics, and async processing 171 - **Claw-Scan Enhancement**: Improved ClawScan (AIG-PromptSecurity) evaluation framework 172 - **Component Fingerprints**: Added 4 new AI component fingerprints for improved detection coverage 173 - llama.cpp, HuggingFace TGI, NVIDIA NIM, LocalAI 174 175 ### Changed 176 - 🐳 **Docker Optimization**: Updated Dockerfile and deployment scripts 177 - Use shallow clone and prefer docker compose v2 in `docker.sh` 178 - Handle chmod failures gracefully in `start.sh` 179 - Updated Dockerfile for Agent-Scan support 180 - 📝 **Documentation Updates**: Comprehensive README updates 181 - Updated README to include Agent Skills in scans 182 - Updated README_ZH.md for clarity and accuracy 183 - Updated research papers and news sections 184 - ⚙️ **Configuration Refactoring**: Removed some provider configurations, restructured field hierarchy 185 - Removed `idSuffix` field and updated related logic 186 - Improved parsing compatibility for config files 187 - Updated config JSON files with icon support 188 189 ### Contributors 190 Special thanks to @rocie799, @Truman, @test0Emma, @hobostay, @Yang Luo, @mhh 191 192 --- 193 194 ## [v3.6.2] - 2026-02-09 195 196 ### Added 197 - 🛡️ **Vulnerability Database Expansion**: Added 78 new CVE entries across 15 AI/ML infrastructure components 198 - **anythingllm** (1): CVE-2025-63390 199 - **comfyui** (2): CVE-2025-67303, CVE-2026-22777 200 - **dask** (1): CVE-2026-23528 201 - **dify** (4): CVE-2025-56157, CVE-2025-63386, CVE-2025-63387, CVE-2025-63388 202 - **feast** (1): CVE-2025-11157 203 - **jupyter-notebook** (1): CVE-2025-53000 204 - **langchain** (4): CVE-2024-58340, CVE-2025-67644, CVE-2025-68664, CVE-2025-68665 205 - **langflow** (9): CVE-2025-34291, CVE-2025-68477, CVE-2025-68478, CVE-2026-0768, CVE-2026-0769, CVE-2026-0770, CVE-2026-0771, CVE-2026-0772, CVE-2026-21445 206 - **lobechat** (1): CVE-2026-23835 207 - **mlflow** (3): CVE-2025-10279, CVE-2025-14279, CVE-2026-22607 208 - **n8n** (33): CVE-2023-27562, CVE-2023-27563, CVE-2023-27564, CVE-2025-46343, CVE-2025-49592, CVE-2025-49595, CVE-2025-52478, CVE-2025-52554, CVE-2025-55526, CVE-2025-57749, CVE-2025-61914, CVE-2025-61917, CVE-2025-62726, CVE-2025-65964, CVE-2025-68613, CVE-2025-68668, CVE-2025-68697, CVE-2025-68949, CVE-2026-0863, CVE-2026-1470, CVE-2026-21858, CVE-2026-21877, CVE-2026-21893, CVE-2026-21894, CVE-2026-25049, CVE-2026-25051, CVE-2026-25052, CVE-2026-25053, CVE-2026-25054, CVE-2026-25055, CVE-2026-25056, CVE-2026-25115, CVE-2026-25631 209 - **ollama** (5): CVE-2025-15063, CVE-2025-15514, CVE-2025-63389, CVE-2025-66959, CVE-2025-66960 210 - **open-webui** (1): CVE-2025-63391 211 - **simstudioai** (8): CVE-2025-7107, CVE-2025-7114, CVE-2025-9800, CVE-2025-9801, CVE-2025-9805, CVE-2025-10096, CVE-2025-10097, CVE-2025-15099 212 - **vllm** (4): CVE-2026-22773, CVE-2026-22778, CVE-2026-22807, CVE-2026-24779 213 214 ### Changed 215 - 📝 **CVE Updates**: Updated existing vulnerability entries for improved accuracy 216 - clickhouse: CVE-2024-23689 217 - gradio: CVE-2024-1728 218 - langchain: CVE-2025-65106 219 - langflow: CVE-2025-57760 220 - mlflow: CVE-2025-11201 221 - vllm: CVE-2025-62164 222 223 --- 224 225 ## [v3.6.1] - 2026-01-27 226 227 ### Added 228 - 🆔 **Component Fingerprints**: Added Clawdbot Gateway fingerprint to improve AI component vulnerability detection coverage. 229 230 ## [v3.6.0] - 2025-01-17 231 232 ### Added 233 - 🔐 **System Administration**: Added SYS_ADMIN capability for Chrome sandbox and database indexes for performance enhancement (@zhuque) 234 - 📊 **Report Enhancement**: Updated feature and pager, resolved text misalignment in PDF report download (@zonashi) 235 - 📝 **User Guide**: Updated user guide for new features (@zonashi) 236 - ⏱️ **Scan Metrics**: Added model & scan duration in AI tool protocol scan report (@zonashi) 237 - 👥 **User Management**: Refactored User struct and enhanced user management methods (@boyhack) 238 239 ### Changed 240 - 📚 **Documentation**: Updated API docs, Swagger docs, and model API (@zhuque) 241 - 🐳 **Docker Config**: Updated docker-compose.yml and docker-compose.images.yml (@zhuque) 242 - 🔢 **Versioning**: Updated version to v3.6.0 (@zhuque) 243 - 🧠 **LLM Result**: Added LLM parameter to MCP meta result (@zhuque) 244 - 🗄️ **Database**: Fixed LLM model database (@zhuque) 245 - 🔐 **Auth**: Implemented inner API auth controller (@zhuque) 246 - 🎯 **Score Correction**: Corrected CalcSecScore method in runner.py to handle Chinese risk levels correctly (@mhh) 247 - ⚖️ **Risk Type**: Corrected item.RiskType to item.Severity in scoring logic (@mhh) 248 249 ### Fixed 250 - 🧪 **Testing**: Removed test info (@zhuque) 251 252 ### Contributors 253 Special thanks to @mhh, @aaasven 254 255 --- 256 257 ## [v3.6.0-rc1] - 2025-01-07 258 259 ### Changed 260 - 🎯 **Audit Prompt Optimization**: Reduced false positives by focusing on network-layer vulnerabilities 261 - Added input source risk priority rules, ignoring CLI inputs 262 - Only report medium+ severity vulnerabilities 263 - Command injection detection excludes CLI parameter scenarios 264 - Credential theft detection requires network exfiltration path 265 - 🔍 **Skill Project Audit**: Improved Skill project security analysis 266 - Skill projects don't require MCP risk classification 267 - Focus on malicious behavior detection (reverse shell, data exfiltration, backdoor, cryptominer) 268 - Ignore code quality and development standard issues 269 - ✅ **Quality Checklist**: Added network reachability verification to vulnerability review 270 271 --- 272 273 ## [v3.5.0] - 2025-12-26 274 275 ### Added 276 - 📚 **Research & Documentation**: Added AIG Technical Report, Black Hat Europe 2025 slides, and Black Hat Arsenal presentation (@hermitgreen, @Nicky, @LouisHovaldt) 277 - 🎓 **Academic Collaborations**: Added academic collaboration section with partner institutions (@zonashi) 278 - 🔍 **Dynamic Analysis Framework**: Complete dynamic analysis workflow with specialized agents for malicious behavior testing and vulnerability testing (@sc, @MoonBirdLin) 279 - 🛡️ **Security Detection**: Tool poisoning detection and rug pull detection support (@sc) 280 - 📊 **Evaluation Datasets**: Added comprehensive test datasets (copyright-violation, misinformation, privacy-leakage, unethical-behavior, violent, non-violent-illegal-activity) (@zonashi) 281 - 🔧 **MCP Tools Enhancement**: Added mcp_tool for remote MCP server tool invocation (@zhuque) 282 - 📝 **File Operations**: Added write_file tool for file writing operations (@zhuque) 283 - 🔌 **Version API**: Added version router endpoint (@zhuque) 284 - 🎯 **Prompt Manager**: Introduced prompt_manager utility for better prompt template management (@zhuque) 285 - 🔐 **MCP Header Support**: Added custom MCP header support for authentication and protocol configuration (@zhuque) 286 287 ### Changed 288 - ♻️ **MCP Architecture Refactoring**: Complete overhaul of MCP agent architecture for better modularity and performance (@zhuque, @MoonBirdLin) 289 - 🎨 **Agent Optimization**: Significantly improved agent prompts and reduced tool execution overhead (@zhuque) 290 - 📦 **Tool System Redesign**: Introduced ToolDispatcher, refactored tool registry, and improved tool schema management (@zhuque) 291 - 🐳 **Docker Optimization**: Further reduced Docker Agent image size and improved Dockerfile structure (@zhuque, @ac0d3r) 292 - 📝 **Logging Enhancement**: Optimized logging system and status update mechanisms (@zhuque) 293 - 🔄 **Prompt Updates**: Comprehensive updates to code audit, project summary, and vulnerability review prompts (@zhuque) 294 - 📦 **Dependencies**: Updated requirements, pinned deepeval to <3.7.6 for compatibility (@zhuque, @Truman) 295 - 🎯 **Scoring Algorithm**: Improved calc_mcp_score function for better vulnerability assessment (@zhuque) 296 - 🌐 **README Updates**: Enhanced README with better structure, GIF demos, and recommended security tools (@zonashi) 297 - 📡 **Backend API Simplification**: Refactored and simplified MCP-scan backend API, reduced code complexity in websocket/api.go (@zhuque) 298 - 📖 **API Documentation**: Updated Swagger documentation with latest API endpoints and improvements (@zhuque) 299 - 🎨 **Frontend UI Optimization**: Enhanced LLM security check experience with prompt input detection support (@zonashi) 300 - 🔧 **Frontend Settings Consolidation**: Merged auxiliary functions (plugin management, model management) into unified settings panel for cleaner interface (@zonashi) 301 - 📋 **Version Display**: Added version number and changelog display in frontend for easier issue tracking (@zonashi) 302 - 🔐 **MCP Header Configuration**: Added MCP scan header configuration in frontend to support MCP service authentication (@zonashi) 303 304 ### Fixed 305 - 🐛 **MCP Agent Bugs**: Fixed various MCP agent bugs and improved stability (@boy-hack, @zhuque) 306 - 🔧 **Execute Actions**: Fixed execute_actions timeout handling and parameter type conversion (@zhuque) 307 - 🎯 **Transport Type**: Fixed server_transport type issue (@sc) 308 - 📊 **Output Handling**: Fixed error output when testing without function invocation but with mcp_function invocation (@MoonBirdLin) 309 - 🛠️ **System Robustness**: Multiple bug fixes for improved system stability (@zhuque, @MoonBirdLin) 310 - 📝 **LLM Integration**: Fixed llm.py parameter handling and retry logic (@zhuque) 311 - 🔐 **Frontend Header Bug**: Fixed AI infrastructure scan header configuration not taking effect (@zonashi) 312 313 ### Contributors 314 Special thanks to @zhuque, @sc, @MoonBirdLin, @zonashi, @Truman, @ac0d3r, @hermitgreen, @Nicky, @LouisHovaldt, @boy-hack 315 316 --- 317 318 ## [v3.5-rc3] - 2025-12-10 319 - fixed mcp-scan not found directory bug 320 - update frontend 321 322 ## [v3.5-preview-2] - 2025-12-05 323 ### Changed 324 - Improved the onboarding guide for frontend newcomers 325 - Vulnerability database: Added 100+ AI component CVEs, with support for detecting the latest React2Shell vulnerability (CVE-2025-55182), which affects popular AI frameworks such as Dify, NextChat, and LobeChat. 326 327 ## [v3.5-preview] - 2025-12-04 328 329 ### Added 330 - 🔍 **MCP-Scan Framework**: AI-powered security scanning framework for Model Context Protocol with autonomous agent-based code audit and vulnerability review (@zhuque) 331 - 🎯 **Advanced Attack Methods**: Added 12+ new encoding/obfuscation attack methods (A1Z26, AffineCipher, AsciiSmuggling, Aurebesh, Caesar, Leetspeak, MirrorText, Ogham, Vaporwave, Zalgo, Stego, StrataSword suite) (@Truman) 332 - 📸 **Screenshot Capabilities**: Chromium-based headless screenshot functionality for web scanning (@zhuque) 333 - 🔐 **Model API Security**: Token masking, API key preservation, and public model access controls (@n-WN) 334 - 📊 **Hash-Based Fingerprinting**: Hash matcher and version range support for component identification (@KEXNA, @Cursor Agent) 335 - 🌐 **Documentation**: Comprehensive English docs, FAQ, MCP-Scan guides, and research paper references (@zonashi, @zhuque) 336 - 🐳 **Docker Optimization**: Reduced agent image size from ~2.9GB to ~2.3GB, improved deployment scripts (@n-WN, @zhuque) 337 338 ### Changed 339 - ♻️ **Backend Refactoring**: Optimized AI infrastructure scan architecture, reduced agent task code by ~65% (@zhuque) 340 - 🔄 **MCP Plugin**: Streamlined plugin architecture, removed redundant templates (@zhuque) 341 - 🚀 **Model Compatibility**: Enhanced parameter compatibility and retry logic across providers (@Truman) 342 - 🎨 **Code Quality**: Translated comments to English, improved formatting and documentation (@zhuque) 343 344 ### Fixed 345 - 🐛 Fixed AI Infra Guard path resolution and Chromium sandbox issues (@zhuque) 346 - 🔧 Fixed Docker deployment errors (issue #105) and build optimizations (@n-WN, @zhuque) 347 - ⚙️ Fixed fingerprint parser syntax and version detection logic (@Cursor Agent, @KEXNA) 348 - 📊 Updated UI badges, screenshots, and license file naming (@zonashi, @Zonazzzz) 349 350 ### Contributors 351 Special thanks to @zhuque, @Truman, @n-WN, @KEXNA, @zonashi, @Cursor Agent, @copilot-swe-agent[bot], @boy-hack, @Zonazzzz, @robertzyang, @Coursen 352 353 --- 354 355 ## [v3.4.4] - 2025-11-05 356 357 ### Fixed 358 1. Fixed issue where prompts could be incorrectly split 359 2. Added generalized model loading logs 360 3. Added model loading parameter combination attempts 361 4. Fixed model invocation parameter compatibility issue 362 5. Optimized log display 363 6. Fixed https://github.com/Tencent/AI-Infra-Guard/issues/110 364 365 ## [v3.4.3] - 2025-10-27 366 ### Added 367 🔧 **API Documentation Support**: Updated and enhanced API documentation support, providing more complete interface documentation and Swagger specifications. 368 🤖 **Model Invocation Base Class**: Added base class methods for model invocation, improving code reusability and maintainability. 369 📊 **Evaluation Dataset Expansion**: Added test datasets related to Cyberattack and CBRN weapons. 370 371 ### Fixed 372 🛠️ **CSV Encoding Issue**: Fixed Chinese garbled text issue in CSV files, improving data export experience. 373 374 ## [v3.4.2] - 2025-09-25 375 - Optimized frontend 376 - Added new vulnerability fingerprints: 377 clickhouse 378 comfyui 379 dask 380 gradio 381 langchain 382 langflow 383 langfuse 384 LiteLLM 385 ollama 386 open-webui 387 pyload-ng 388 ragflow 389 ray 390 triton-inference-server 391 vllm 392 393 394 ## [v3.4.1] - 2025-09-24 395 - Added vulnerability fingerprint CVE-2025-23316 396 - Optimized: triton fingerprint 397 398 ## [v3.4] - 2025-09-18 399 ### Added 400 🌐 **Internationalization Support**: Implemented frontend interface internationalization (i18n) support, including multi-language text and English screenshot resources. 401 🐳 **Docker Enhancement**: Updated one-click deployment script, added Docker pull error information prompt, and supported Apple ARM architecture deployment. 402 ⚡ **Task Concurrency Control**: Added task concurrency limit feature, optimized system resource management. 403 🔄 **Model Retry Logic**: Updated model invocation retry mechanism, improving service stability. 404 🤖 **Agent Auto-Recovery**: Implemented automatic restart function after Agent process abnormal exit. 405 📚 **Multi-Dataset Compatibility**: Enhanced compatibility handling for multiple dataset formats. 406 🔌 **OpenAPI Interface Update**: Handled the issue of thinking model thinking process being too long. 407 408 ### Fixed 409 🛠️ **Frontend Issue Fix**: Fixed frontend interface display issues, including narrow screen adaptation and specific UI anomalies (#74). 410 🔧 **MCP Issue Fix**: Fixed known bugs in MCP protocol, including model output processing and connection stability. 411 ⚙️ **Parameter Parsing Error**: Fixed exception issues in parameter parsing process. 412 📊 **Evaluation Exception Fix**: Fixed abnormal behavior in evaluation module. 413 🔄 **Task Reset Failure**: Fixed the issue of task reset operation failure while running. 414 🛡️ **Security Risk Fix**: Fixed security risk issues related to IP checking (#78). 415 🔗 **Circular Import Issue**: Fixed possible circular import errors in code. 416 📝 **License Update**: Updated project license files. 417 418 ## [v3.3] - 2025-09-03 419 - Added one-click Docker deployment script for Linux 420 - Fixed SSE connection failure issue when disk read/write is slow 421 - Optimized AI infrastructure scanning probe 422 423 ## [v3.2] - 2025-08-26 424 425 ### Added 426 427 - 📊 **MCP Scan Report Optimization**: Added more dimensions of detection data display, improving user experience. 428 - 📱 **Narrow Screen Security Report Adaptation**: Optimized the display of large model security check reports on narrow screens. 429 - ⚙️ **New Model Concurrency Limit**: Introduced new model concurrency limit feature. 430 431 ### Fixed 432 433 - 🔌 **Fixed MCP SSE Timeout Issue**: Resolved the timeout issue of Server-Sent Events (SSE) in MCP (Model Control Protocol). 434 - ❓ **Fixed MCP Model Empty Output Exit Issue**: Resolved the issue where the system would exit when MCP model output is empty (#61). 435 - 📋 **Updated MCP Hardcoded Template**: Updated the hardcoded template for MCP. 436 - 🛡️ **Fixed AIG Prompt IP Check Risk**: Fixed security risks related to IP checking in AIG prompts.