oss-repo-setup
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various CLI tools including git, gh, pnpm, and node to manage repository states, install dependencies, and configure GitHub settings through the gh API.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the repository and environment to customize templates, which creates a potential vector for indirect injection if repository contents are malicious.\n
- Ingestion points: Repository metadata such as package.json contents, .node-version, and Git remote URLs are read via the scripts/scaffold.mjs script.\n
- Boundary markers: None. The template interpolation process does not use explicit delimiters or markers to isolate external data from the instructions.\n
- Capability inventory: The skill has broad capabilities including local file system modification, package installation (pnpm install), and remote repository management (git push, gh repo edit).\n
- Sanitization: Template placeholders are filled using simple string replacement in the scaffold script without specialized sanitization or context-aware escaping.
Audit Metadata