grilling
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans and ideas and compares them against information found in the local environment to verify facts. This establishes a vulnerability surface where untrusted data is processed in the same context as environment lookups.
- Ingestion points: User input regarding plans or decisions (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill instructions permit use of tools and filesystem access to retrieve information (SKILL.md).
- Sanitization: No sanitization or input validation is specified for the user-provided data.
Audit Metadata