ugc-supplements
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains no executable scripts, binaries, or source code files. It consists entirely of documentation and templates for generating text-based prompts for an external API.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8).
- Ingestion points: Multiple templates in 'SKILL.md' (e.g., Morning Stack, Gym Bag Dump) accept user-supplied content via placeholders like '[PRODUCT]', '[SUPPLEMENT LIST]', and '[ADDITIONAL DETAILS]'.
- Boundary markers: There are no protective delimiters, such as XML tags or backticks, or 'ignore instructions' warnings surrounding the user-provided placeholders.
- Capability inventory: The prompts are intended to be passed to a tool for executing 'POST /videos/generate' requests.
- Sanitization: The skill does not implement any escaping, validation, or instructions to the agent to filter or ignore potentially malicious instructions embedded in the user's input.
Audit Metadata