writing-plans
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests external specifications to generate implementation plans, creating a surface for indirect prompt injection.
- Ingestion points: Specification and requirement data provided as input for plan generation in SKILL.md.
- Boundary markers: Absent. The skill does not define delimiters for the input spec.
- Capability inventory: The skill is capable of writing files to the local file system (docs/superpowers/plans/) and can invoke sub-agents or execution tools like superpowers:subagent-driven-development.
- Sanitization: Absent. No filtering or validation of the input specification is mentioned.
- Mitigation: A separate prompt template (plan-document-reviewer-prompt.md) is used to review the generated plans for completeness and errors, which provides a layer of oversight.
Audit Metadata