grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or format files.
- [DATA_EXPOSURE]: The skill explores the codebase and documentation to gather context for domain modeling. This access is limited to the project environment and does not involve accessing sensitive system files or exfiltrating data.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase (Ingestion point: src/, CONTEXT.md) to inform its documentation updates. While no explicit boundary markers or sanitization logic are defined, its write capabilities are limited to documentation files (Capability inventory: write_file for .md files), which poses a very low risk.
Audit Metadata