intent-layer

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a utility for organizing and maintaining agent-friendly repository context through AGENTS.md and CLAUDE.md files.
  • [SAFE]: Automated analysis scripts (analyze_structure.sh, detect_state.sh, estimate_tokens.sh, check_context_staleness.sh) utilize standard Unix utilities for local file system inspection and do not perform any network operations.
  • [SAFE]: The staleness checking logic uses file path heuristics to prioritize documentation review, which is a legitimate maintenance function and does not involve exfiltration of sensitive data.
  • [SAFE]: All components are local; there are no external dependencies, remote script downloads, or dynamic execution of untrusted code.
  • [SAFE]: The skill does not request elevated privileges or attempt to establish persistence on the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 06:08 AM
Security Audit — agent-trust-hub — intent-layer