@tank/agents-md

Pass

Audited by Gen Agent Trust Hub on May 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structural templates and guidelines for instruction files such as AGENTS.md and CLAUDE.md, containing no functional code or automation logic.
  • [SAFE]: No network activity, external resource fetching, or data exfiltration patterns were detected in the analysis of the documentation files.
  • [SAFE]: There is no evidence of obfuscation, multi-layer encoding, or hidden instructions within the skill's repository.
  • [SAFE]: The skill explicitly promotes security best practices, such as instructing agents never to commit secrets or environment files.
  • [SAFE]: Filesystem permissions are limited to reading project files, which is necessary for the stated purpose of managing directory-scoped instruction hierarchies, and no mechanism for exfiltration is present.
Audit Metadata
Risk Level
SAFE
Analyzed
May 31, 2026, 11:04 PM
Security Audit — agent-trust-hub — @tank/agents-md