setup-ts-deep-modules

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a persistence mechanism by adding architectural instructions to agent-facing configuration files (CLAUDE.md or AGENTS.md), which influences the behavior of future agent sessions.
  • Ingestion points: The agent reads instructions from CLAUDE.md or AGENTS.md at the start of new sessions.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded content are provided for the injected text.
  • Capability inventory: The skill possesses file-writing capabilities and can execute shell commands via package managers (SKILL.md).
  • Sanitization: The skill does not perform sanitization on the content written to the instruction files.
  • [EXTERNAL_DOWNLOADS]: The skill installs the dependency-cruiser utility from the official npm registry using the project's detected package manager.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the detected package manager (npm, pnpm, yarn, or bun) to detect the environment, install development dependencies, and run validation checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:32 PM
Security Audit — agent-trust-hub — setup-ts-deep-modules