grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and configuration metadata. There are no scripts, binaries, or automated command executions identified.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to inspect repository artifacts and configuration files, which constitutes a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Local repository files, configuration, and artifacts as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters for separating repository content from instructions.
- Capability inventory: None. The skill explicitly states it is an "interview workflow, not authorization to implement or modify anything" and forbids implementation, external writes, or mutations in
SKILL.md. - Sanitization: No explicit sanitization or filtering of ingested file content is defined.
Audit Metadata