ClawAudit verdict

rag-accuracy-optimizer

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Pure documentation skill providing RAG system optimization guidance (DB schema patterns, chunking strategies, retrieval techniques); no execution sinks, no network calls, behavior is entirely advisory.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

30
security
60
transparency
70
maintenance

Findings (3)

Pattern match critical

Prompt injection — tries to override agent instructions

references/testing-frameworks.md · code · Ignore previous instructions

Pattern match critical

Pipe to python — executes piped content as Python code

references/testing-frameworks.md · code · | python

Pattern match medium

Python os.getenv — reads environment variable

references/orchestrator-patterns.md · code · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

data_encoding

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API