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.jsonand MCP settings, as sensitive data and explicitly instructs the agent to avoid migrating or modifying them. - [SAFE]: It utilizes local Python scripts (
scripts/precheck.pyandscripts/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