setup-ts-deep-modules
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the project's detected package manager (npm, pnpm, yarn, or bun) to install
dependency-cruiseras a development dependency. It also executesdepcruiseto verify that the newly configured boundary rules are working as intended. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads and acts upon external repository data.
- Ingestion points: The skill reads
pnpm-lock.yaml,yarn.lock,bun.lockb, and the directory structure (e.g.,src/packages) to determine the environment. - Boundary markers: None identified for the ingested file content.
- Capability inventory: The skill can execute package manager commands, modify
package.jsonscripts, write configuration files (.dependency-cruiser.cjs), and update project documentation (CLAUDE.md,AGENTS.md). - Sanitization: No specific sanitization is performed on the ingested path names or configuration strings beyond standard shell execution.
Audit Metadata