nuke-test
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill resolves and executes shell commands defined in target repository manifest files like package.json or Makefile to perform testing and linting.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and configuration files which serves as context for behavior mapping and test generation.
- Ingestion points: Project source code and manifest files read from the local file system.
- Boundary markers: Agent orchestration uses file paths and specific artifacts to maintain thin context.
- Capability inventory: The skill can read/write files and execute shell commands through local test runners.
- Sanitization: No explicit sanitization of codebase content is mentioned before agent processing.
Audit Metadata