grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for documentation and architectural refinement. It interacts with the user and the codebase for legitimate development workflows. No malicious intent or suspicious patterns were found.- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes data from the repository, a risk factor typical for codebase-aware tools.
- Ingestion points: Reads files from the source code and documentation directories.
- Boundary markers: Does not implement explicit markers to delimit untrusted data from the agent's instructions.
- Capability inventory: The agent has capabilities to read from and write to the local filesystem.
- Sanitization: No content validation or sanitization is performed on the data ingested from the project files.
Audit Metadata