rheged-skills-setup
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a JSON catalogue of available skills from the vendor's GitHub repository to facilitate batch installation. Evidence: scripts/lib/catalogue.mjs defines DEFAULT_CATALOGUE_URL as a vendor resource URL on GitHub.
- [COMMAND_EXECUTION]: The skill utilizes system commands to detect repository state and manage configuration. Evidence: Executed commands include git for branch and issue key detection, gh for verifying the presence of GitHub Actions secrets, and npx skills for installing remote skill bundles.
- [INDIRECT_PROMPT_INJECTION]: The skill processes local repository metadata and user-supplied facts to generate configuration files, which represents an attack surface for indirect injection. Ingestion points: The skill reads package.json, pnpm-workspace.yaml, and config.example.json from the host repository. Boundary markers: The process includes a dry-run phase and requires explicit user confirmation before writing changes. Capability inventory: The skill has the ability to write to config.json files, modify the .gitignore, and maintain a .claude/skills.lock file. Sanitization: Input values are validated against type-safe placeholders defined in example configurations.
Audit Metadata