grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script to maintain project knowledge when specific conditions are met.
  • Evidence: node docs/agents/project-knowledge.mjs maintain in SKILL.md.
  • Context: This appears to be a standard operational command for managing local metadata and rules related to the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes untrusted data from external sources.
  • Ingestion points: Processes project context from project-knowledge load, user-supplied plans, and code files read from the environment.
  • Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the project files are defined.
  • Capability inventory: The agent can execute a specific Node.js script and dispatch sub-agents to read the file system and use tools.
  • Sanitization: No explicit sanitization of external content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 03:54 PM
Security Audit — agent-trust-hub — grill-with-docs