spanish-cooking-expert
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates a mandatory research workflow that directs the agent to fetch and integrate content from external websites and platforms (e.g., Wikipedia, expert articles).
- Ingestion points: The
modules/research-checklist.mdfile instructs the agent to perform targeted web searches and record sources to validate legacy guidance. - Boundary markers: There are no instructions providing delimiters or specific warnings to ignore embedded instructions within the gathered research data.
- Capability inventory: The skill recommends the use of external research tools (e.g.,
adn_skills) to process potentially untrusted third-party content. - Sanitization: No sanitization, filtering, or validation steps are defined for the information retrieved from external sources before it is used to update the skill's core guidance.
Audit Metadata