writing-plans
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a template for creating implementation plans and does not perform any dangerous operations. All referenced tools and workflows are standard for development environments.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate plans that are then used by other agents, creating a potential surface for indirect prompt injection.
- Ingestion points: User-provided feature descriptions and repository context (SKILL.md).
- Boundary markers: The skill uses markdown headers to separate task sections but does not include explicit instructions to ignore malicious embedded content in the user input (SKILL.md).
- Capability inventory: The generated plans are intended to be executed by skills like superpowers:subagent-driven-development, which likely have file-writing and command-execution capabilities (SKILL.md).
- Sanitization: No input validation or sanitization is performed on the user input before it is incorporated into the plan document.
Audit Metadata