agents-md-ssot

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary behavior involves reading and refactoring local documentation files (CLAUDE.md, AGENTS.md, and the MEMORY/ directory) to ensure cross-agent compatibility.
  • [SAFE]: The skill identifies sensitive configuration files, such as .claude/settings.local.json and MCP settings, as sensitive data and explicitly instructs the agent to avoid migrating or modifying them.
  • [SAFE]: It utilizes local Python scripts (scripts/precheck.py and scripts/coverage.py) for workflow validation. These scripts use standard Python libraries to perform file existence checks and token-based text comparison; no network activity or data exfiltration patterns were detected in the source code.
  • [SAFE]: All processes are transparently documented with interactive confirmation points for the user. No obfuscation, remote code execution, or suspicious persistence mechanisms are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 06:05 PM
Security Audit — agent-trust-hub — agents-md-ssot