registry-browser
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches skill definitions and directory indexes from external GitHub repositories. This behavior is the primary intended function of the skill and uses well-known services (GitHub) to retrieve data for user review.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of remote SKILL.md files and metadata. While this creates a surface where a malicious repository could include instructions designed to influence the agent during the preview step, the workflow explicitly includes a human-in-the-loop requirement where the user must review the full SKILL.md before any further action is taken.
- [DATA_EXPOSURE]: The skill reads from a local configuration file at
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.mdto manage the list of registries. This is standard configuration management for the skill's specific purpose.
Audit Metadata