Acacian/aegis
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
10 starsPythonMITai-governanceai-safetylangchainpolicy-engine
REVIEWED76/100
Scanned 2026-06-25 · gemini v1
Dimension breakdown
Security
55/100
3 findings
Quality
98/100
2 findings
License
90/100
No findings
Completeness
60/100
5 findings
Findings (10)
CRITICAL: 1HIGH: 2MEDIUM: 3INFO: 4
- CRITICALcompletenessMissing `server.json` manifest
- HIGHsecurityPotential YAML Deserialization Vulnerability
- HIGHcompletenessUndocumented MCP Server Tools
- MEDIUMsecurityInsufficient Input Validation in CLI/Server Components
- MEDIUMsecurityPotential Server-Side Request Forgery (SSRF) via HTTP Egress
Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.
Maintainer of this repo?
Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.
Claim listingEmbed the badge.
Drop it into your README. Every view backlinks to this verification page.
Markdown
[](https://archimedes.market/r/Acacian/aegis)HTML
<a href="https://archimedes.market/r/Acacian/aegis"><img src="https://archimedes.market/api/badge/Acacian/aegis.svg" alt="Archimedes Trust Verified"/></a>