setup-ts-deep-modules

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs dependency-cruiser as a development dependency via the detected package manager. This is a well-known open-source tool for enforcing module boundaries.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads project configuration files and repository metadata to customize the setup process. This presents a theoretical vulnerability surface where a maliciously crafted repository could influence agent behavior, though the risk is inherent to development tooling.
  • Ingestion points: pnpm-lock.yaml, yarn.lock, bun.lockb, .dependency-cruiser.*, and repository file paths.
  • Boundary markers: No explicit markers are used to separate ingested file content from the agent's system instructions.
  • Capability inventory: File system writes (configuration, example code, and README files) and shell command execution (package manager install and run commands).
  • Sanitization: No sanitization is performed on the ingested project filenames or configuration content before it is used to determine build commands and file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:57 AM
Security Audit — agent-trust-hub — setup-ts-deep-modules