understand-onboard

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill focuses on reading a local JSON file and generating a markdown document. It uses standard file reading and grep operations to extract project structure and documentation details.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a codebase-derived JSON file which could contain malicious content, though the impact is low as it only outputs static documentation.
  • Ingestion points: .understand-anything/knowledge-graph.json
  • Boundary markers: None present in the instructions.
  • Capability inventory: File system write access to create docs/ONBOARDING.md.
  • Sanitization: None specified for the extracted JSON content before inclusion in the markdown guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:30 PM
Security Audit — agent-trust-hub — understand-onboard