hook
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content to generate opening hooks, creating a surface for indirect prompt injection where malicious instructions within the input could potentially influence the agent's behavior. 1. Ingestion points: User-provided content types, drafts, and topic descriptions processed in SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within user-provided content. 3. Capability inventory: The skill invokes other agent capabilities such as creator-stack:voice and creator-stack:brand-guidelines. 4. Sanitization: No specific sanitization or filtering logic is defined for the user-supplied content.
Audit Metadata