grill-with-docs

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is focused on domain modeling and documentation maintenance. It contains no commands for network exfiltration, credential access, or unauthorized execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to read and process the local codebase.
  • Ingestion points: The skill reads CONTEXT.md, CONTEXT-MAP.md, ADR files, and source files in the src/ directory to build context.
  • Boundary markers: No explicit markers are used to isolate content read from the codebase from the agent's instructions.
  • Capability inventory: The skill can read project files and write updates to documentation (CONTEXT.md, ADRs).
  • Sanitization: No specific sanitization or validation of the ingested file content is performed before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 03:25 AM