heal-skill
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a set of structural maintenance tools for managing an AI skill repository.
- The
heal.shscript performs structural audits such as verifying YAML frontmatter (name, description, stability), checking for unlinked or dead file references, and validating CLI subcommands. - File modifications (auto-fixing) are performed safely using temporary files and standard utilities like
sed,awk, andmktemp. - The script's operations are strictly scoped to the local
skills/andskills-codex/directories. - It includes logic to validate
aoCLI subcommands by executingao help, which is a standard procedure for CLI-integrated tools. - No network exfiltration, sensitive data access, or malicious injection patterns were detected across the analyzed files.
Audit Metadata