task-runner
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses on process adherence, human review, and task verification.
- [DATA_INGESTION]: The skill is designed to ingest and process implementation plan files. While these files are external and could potentially contain malicious instructions (Indirect Prompt Injection surface), the skill mandates a 'Prime Directive' of critical scrutiny and human review between batches to mitigate such risks.
- Ingestion points: Implementation plan files (referenced in SKILL.md Step 1).
- Boundary markers: Relies on the 'Prime Directive' and manual scrutiny rather than technical delimiters.
- Capability inventory: The skill coordinates task execution and verification, likely leveraging the agent's underlying shell or tool capabilities.
- Sanitization: Relies on human architect review between batches to identify and correct plan errors or malicious intent.
Audit Metadata