spec-plan
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (spec.md) and human annotations to generate implementation plans. These plans include shell commands and code snippets intended for later execution by an engineer or subsequent automation skills.
- Ingestion points: Processes spec.md and user-provided annotations.
- Boundary markers: No explicit delimiter markers are used during the ingestion of specification files.
- Capability inventory: While this skill does not execute code itself, it generates a plan.json file containing instructions for file modifications and terminal commands.
- Sanitization: Security is primarily managed via a 'sacred' human review cycle where the plan must be explicitly approved before task conversion occurs.
Audit Metadata