skills/agentskillexchange/skills/Use RAGFlow as a retrieval and context layer for agent workflows/Gen Agent Trust Hub
Use RAGFlow as a retrieval and context layer for agent workflows
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch the project repository and Docker images from official GitHub and Docker Hub sources for deployment. * Evidence: git clone and docker compose commands provided in the Installation section of SKILL.md.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of a RAG context layer, which introduces an attack surface where instructions embedded in retrieved documents could influence agent behavior. * Ingestion points: User-provided source document corpus indexed by RAGFlow. * Boundary markers: Absent; no instructions for using delimiters or protective prompting are provided in the skill instructions. * Capability inventory: The agent retrieves grounded context to answer queries and perform workflows based on the indexed data. * Sanitization: Absent; no mention of content filtering or validation for indexed documents in the deployment instructions.
Audit Metadata