A benchmark and generation framework for malicious agent skills.
Like lxyeternal/MalSkillBench, 0 likes 0 Bookmark lxyeternal/MalSkillBench, 0 bookmarks 0 [ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
Like LeiLiLab/susvibes, 0 likes 0 Bookmark LeiLiLab/susvibes, 0 bookmarks 0 Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.
Like Berserk-hub150/skillhawk, 0 likes 0 Bookmark Berserk-hub150/skillhawk, 0 bookmarks 0 A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Like ethz-spylab/agentdojo, 0 likes 0 Bookmark ethz-spylab/agentdojo, 0 bookmarks 0 [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Like AI-secure/RedCode, 0 likes 0 Bookmark AI-secure/RedCode, 0 bookmarks 0 Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Like NVIDIA/SkillSpector, 3 likes 3 Bookmark NVIDIA/SkillSpector, 4 bookmarks 4 Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, and more
Like akanthed/SecureAI-Scan, 0 likes 0 Bookmark akanthed/SecureAI-Scan, 0 bookmarks 0 [No longer actively maintained] Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applications.
Like cybozu/prompt-hardener, 0 likes 0 Bookmark cybozu/prompt-hardener, 0 bookmarks 0 SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).
Like alibaba/sec-code-bench, 0 likes 0 Bookmark alibaba/sec-code-bench, 0 bookmarks 0