writing-plans
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied specifications and requirements to generate detailed implementation plans containing code and shell commands. This creates a potential surface for indirect prompt injection where malicious instructions in a requirement document could influence the generated output.
- Ingestion points: Processes external project requirements and specifications.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat input requirements as data rather than instructions.
- Capability inventory: The skill performs file writing operations to the
docs/plans/directory and prepares commands for execution by downstream skills. - Sanitization: The instructions do not specify any validation or sanitization steps for the input data before it is transformed into a plan header or task description.
Audit Metadata