pets-and-animals-lead-by-18gc2qf
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a text-based workflow for planning and storyboarding AI videos. It lacks execution capabilities, network operations, or credential access.
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect injection via user-provided character and action requirements (SKILL.md). A structured 'Preserve / Replace / Avoid' contract acts as a logical boundary to guide input processing. The skill's capabilities are restricted to producing text-based video prompts and motion briefs, presenting no significant security risk. No specific sanitization of user input was identified.
Audit Metadata