grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to facilitate architectural discussions and maintain project documentation like CONTEXT.md and Architectural Decision Records (ADRs). Analysis of the instructions and supporting files revealed no evidence of prompt injection, data exfiltration, persistence mechanisms, or unauthorized command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data by reading existing codebase documentation and files (SKILL.md, CONTEXT.md) to stress-test designs. Ingestion points: reads codebase and doc files; Boundary markers: none; Capability inventory: file-writes to documentation; Sanitization: none. This ingestion surface is considered safe as the agent's capabilities are restricted to documentation management and user dialogue, with no access to sensitive system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:59 PM
Security Audit — agent-trust-hub — grill-with-docs