cook-parallel
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implementation in SKILL.md defines a legitimate orchestration workflow with strict protocols to prevent context loss and maintain code quality.
- [PROMPT_INJECTION]: A surface for indirect prompt injection exists in SKILL.md as the skill processes user-defined task arguments and project documentation.
- Ingestion points: The skill ingests the $ARGUMENTS variable for task decomposition and reads local markdown files for context.
- Boundary markers: No explicit boundary markers or delimiters are used to wrap external data within the orchestration process.
- Capability inventory: The skill coordinates subagents which possess the capability to modify the filesystem, write source code, and execute integration tests.
- Sanitization: The workflow relies on agent reasoning and logical separation rather than explicit programmatic sanitization of input data.
Audit Metadata