fb-engagement-drafter
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and draft replies for user-provided comments from Facebook. This represents an indirect prompt injection attack surface where malicious instructions embedded in a comment could potentially be executed by the agent.
- Ingestion points: The skill requests the user to paste comments under a Page post (SKILL.md, Step 2).
- Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the user-pasted comments from the agent's instructions.
- Capability inventory: The skill utilizes
lib.publishto output drafts and reads external context fromvoice-profile.md. - Sanitization: No explicit sanitization or filtering of the input text is mentioned before processing.
Audit Metadata