test-running
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to discover and run shell commands for testing, including 'npm test', 'make test', and any scripts matching './bin/test-*' or 'test'.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by design. It instructs the agent to execute commands found in untrusted repository files without validation. Ingestion points: Documentation (README.md, AGENTS.md, CLAUDE.md) and configuration files (package.json, Makefile, pyproject.toml, Cargo.toml) as defined in SKILL.md. Boundary markers: None present; the instructions do not include warnings to ignore instructions embedded in the data. Capability inventory: Execution of arbitrary shell commands. Sanitization: None; the skill mandates running discovered commands until 100% success is achieved.
Audit Metadata