working-in-parallel
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill instructs agents to follow setup commands in project-specific files such as README.md. Ingestion points: README.md, AGENT.md, and claude.md. Boundary markers: Absent. Capability inventory: git, bun, npm, pnpm, and gh. Sanitization: Absent.
Audit Metadata