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
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:23 AM