agentic_security
https://github.com/msoedov/agentic_security
Python
Agentic LLM Vulnerability Scanner / AI red teaming kit
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported0 Subscribers
Add a CodeTriage badge to agentic_security
Help out
- Issues
- Fix/msj call site and litellm isinstance
- fix: msj_data prepare_prompts ignores dataset_names parameter and uses mutable default
- Epic: Collapse to CLI — remove MCP + Agno, make scanning agent-invocable
- Phase 3: Add stateless `scan` CLI command (agent-invocable)
- Add logging to MCP main functions
- Add type hints to MCP main.py local variables
- Add type hints to MCP function parameters and return types
- Add specific type hints to MCP tool functions
- Best-practice: wildcard CORS w/ credentials + path-traversal defense-in-depth on /icons proxy
- docs: add MCP client usage example
- Docs
- Python not yet supported