grill
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a conceptual workflow for fact-checking and structured communication. It does not contain executable code, shell commands, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data, which is inherent to its fact-checking functionality.
- Ingestion points: External 'research files', the 'body repo', and other tools referenced at runtime (SKILL.md).
- Boundary markers: None identified to separate external file content from the agent's internal instruction context.
- Capability inventory: The skill is authorized to write to local files including
decisions/,context/glossary.md, andcontext/open-questions.md(SKILL.md). - Sanitization: No specific sanitization or filtering logic is defined for the content extracted from external research files.
Audit Metadata