grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is instructed to interact with the file system by exploring the codebase to resolve facts and by creating or updating documentation files, specifically 'CONTEXT.md', 'CONTEXT-MAP.md', and ADRs within the 'docs/adr/' directory.
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface as it is designed to ingest and process untrusted data from the repository's codebase to inform its analysis.
  • Ingestion points: Instructions in 'SKILL.md' direct the agent to explore the codebase and read existing documentation files ('CONTEXT.md', 'CONTEXT-MAP.md').
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore potential commands embedded in the codebase files.
  • Capability inventory: The agent has the ability to read arbitrary files in the codebase and write/update documentation files.
  • Sanitization: Absent; the skill does not specify any validation or sanitization for the content ingested from the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 03:47 PM
Security Audit — agent-trust-hub — grill-with-docs