ugc-dtc
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user data and interpolate it into templates that drive an external video generation tool.
- Ingestion points: User-provided details for products, brands, and usage scenarios are captured via
[BRACKETED]placeholders throughoutSKILL.md. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" directives to prevent the agent from obeying malicious instructions embedded within the user-supplied data.
- Capability inventory: The skill is intended to construct payloads for a
POST /videos/generateAPI endpoint. - Sanitization: There is no evidence of input validation, escaping, or filtering to ensure that user input does not alter the intended structure of the video generation prompt.
Audit Metadata