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