grill-me
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to "explore the codebase" to answer questions. This creates an indirect prompt injection surface where the agent processes untrusted data from external files.
- Ingestion points: Data from the local codebase enters the agent's context when following the instructions in SKILL.md.
- Boundary markers: No delimiters or safety warnings are present in SKILL.md to differentiate between instructions and data found in the codebase.
- Capability inventory: The skill leverages the agent's file system reading capabilities to fulfill the user's request.
- Sanitization: No explicit sanitization or validation of the content retrieved from the codebase is defined.
- [NO_CODE]: The skill consists entirely of markdown instructions without any accompanying scripts, binaries, or configuration files.
Audit Metadata