setup-ts-deep-modules
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the system's detected package manager (npm, pnpm, yarn, or bun) to install development dependencies and run dependency-cruiser commands.
- [EXTERNAL_DOWNLOADS]: Fetches the
dependency-cruiserpackage from the official registry as part of the setup process. - [INDIRECT_PROMPT_INJECTION]: The skill adapts its configuration based on existing files found in the target repository, creating a surface for indirect instructions to influence the agent.
- Ingestion points: Reads lockfiles (pnpm-lock.yaml, etc.),
.dependency-cruiser.*,tsconfig.json, and agent instruction files (CLAUDE.md,AGENTS.md) from the repo root. - Boundary markers: None present; the agent treats the content of these files as configuration data, though it is instructed to confirm choices with the user.
- Capability inventory: The skill possesses the ability to install packages, write new configuration files, and execute linting scripts via the shell.
- Sanitization: The agent does not explicitly validate the content of the repository files before using them to determine command parameters or file paths.
Audit Metadata