rag-knowledge
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a Retrieval-Augmented Generation (RAG) system that ingests external data.
- Ingestion points: In SKILL.md, ingestion points are identified in the 'rag-ingest' command (targeting local files) and 'rag-source-sync' (connecting to Google Drive and S3/MinIO).
- Boundary markers: The instructions in SKILL.md lack specific guidance on using delimiters or instructions to ignore malicious prompts embedded within the ingested documents.
- Capability inventory: As seen in SKILL.md, the agent can execute various CLI commands (rag-ingest, rag-search, rag-drop) via 'uv run' to modify and query the knowledge base.
- Sanitization: No sanitization or content filtering logic is described in SKILL.md for the ingested document content.
Audit Metadata