ugc-lifestyle-broll
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill templates in SKILL.md interpolate user-supplied data directly into prompts for a video generation API tool.
- Ingestion points: Multiple placeholders such as [PRODUCT], [SURFACE], and [ADDITIONAL DETAILS] are designed to accept arbitrary user input in SKILL.md.
- Boundary markers: The templates do not employ delimiters (such as triple quotes or XML tags) or specific instructions to help the model distinguish between developer instructions and user-provided data.
- Capability inventory: The skill is intended to trigger the POST /videos/generate tool based on these constructed prompts.
- Sanitization: There is no evidence of input validation, escaping, or filtering for the user-provided strings before they are processed by the agent.
Audit Metadata