Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, user input in system prompts, over-broad tools, MCP servers without auth, leaked keys and unsafe model loading. 36 tested rules, CWE and OWASP mapping.
Cross-referenced across 55 tracked directories
#2867
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
10/4/2026
Created
1
GitHub Stars
2
Forks
4
Open Issues
10/16/2026
Last Commit
Recently added to the ecosystem
Score: 71/100
0 dependency vulnerabilities found
bytedance
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Erick Friis <[email protected]>
Building applications with LLMs through composability
Joao Moura <[email protected]>
Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
...more