grill-with-docs

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill is designed for documentation maintenance and operates within expected parameters.- [DATA_EXFILTRATION]: The skill accesses the local filesystem to read source code and project documentation. This is necessary for its intended functionality and no exfiltration mechanisms to external domains were detected.- [PROMPT_INJECTION]: The skill reads data from the codebase which constitutes an Indirect Prompt Injection surface (Category 8).
  • Ingestion points: Local source code and documentation files like CONTEXT.md and CONTEXT-MAP.md.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: Local file read/write access for documentation management; no network or execution capabilities.
  • Sanitization: No explicit sanitization of codebase content is mentioned. The risk is assessed as safe given the narrow and local scope of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 04:49 PM
Security Audit — agent-trust-hub — grill-with-docs