Skills
Navigate
skills/moonlight-lupin/agent-skills/library-rag/Snyk

library-rag

Warn

Audited by Snyk on Aug 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). MCP tool search(query=...) in scripts/mcp_server.py takes outsider-supplied free-text query at runtime, embeds it via rag_common.get_embedding(), and uses it to retrieve LLM-readable chunk_text from the indexed sqlite-vec library.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 15, 2026, 06:15 PM
Issues
1
Security Audit — snyk — library-rag