writing-plans
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external specifications or requirements to generate structured implementation plans, which presents an attack surface where untrusted input could attempt to influence the output.
- Ingestion points: Input requirements or specifications for multi-step tasks.
- Boundary markers: The instructions do not specify delimiters or safety warnings for the input data.
- Capability inventory: The skill generates plans containing shell commands (git, pytest), writes files to the local directory (docs/plans/), and delegates tasks to other sub-skills.
- Sanitization: No explicit sanitization or input validation steps are described within the skill instructions.
- [DYNAMIC_EXECUTION]: The skill generates specific code blocks and shell commands within plan documents for subsequent execution by the agent or sub-agents, representing a standard template-based generation pattern for development workflows.
Audit Metadata