setup-ts-deep-modules
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
dependency-cruiserpackage as a development dependency using standard package managers (npm, yarn, pnpm, or bun). - [COMMAND_EXECUTION]: The skill executes shell commands to detect the repository's environment, install dependencies, and verify the configuration by running linting checks.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading repository data and modifying files that guide future agent behavior.
- Ingestion points: The skill reads repository lockfiles (
pnpm-lock.yaml,yarn.lock,bun.lockb) and existing.dependency-cruiser.*configuration files (SKILL.md, Step 1). - Boundary markers: There are no explicit delimiters or instructions to treat existing repository configurations as untrusted data.
- Capability inventory: The skill can execute shell commands for installation and linting, write new configuration and documentation files, and append instructions to agent-specific files (
CLAUDE.mdorAGENTS.md). - Sanitization: The process for merging existing configuration files into the new boundary rules does not specify sanitization or validation of the input content.
Audit Metadata