rag-engineer
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides best practices and architectural patterns for RAG engineering without any evidence of malicious intent or dangerous instructions.\n- [NO_CODE]: There are no scripts, binaries, shell commands, or package requirements defined in the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes explicit instructions for the agent to treat retrieved content as untrusted evidence and to enforce authorization boundaries, which serves as defensive guidance against potential indirect prompt injection attacks in systems designed using these principles.
Audit Metadata