ugc-dtc
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of Markdown documentation and templates. It does not include any executable code, scripts, or remote dependencies.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. Ingestion points: SKILL.md defines templates that utilize placeholders like [PRODUCT] and [BRAND] for user input. Boundary markers: No delimiters or isolation instructions are used to separate user data from prompt logic. Capability inventory: The skill directs the agent to interact with the POST /videos/generate API endpoint, facilitating network operations. Sanitization: No input validation or sanitization logic is provided for the interpolated data.
Audit Metadata