writing-plans
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8).
- Ingestion points: It processes technical "specs" or "requirements" as the primary input for generating plans (as defined in SKILL.md).
- Boundary markers: The skill does not utilize specific delimiters or instructions to prevent the agent from obeying malicious instructions embedded within the input specification.
- Capability inventory: The skill is designed to write plan files to the local filesystem (docs/superpowers/plans/) and generate shell commands including 'pytest', 'git', and 'bash' for subsequent execution by subagents or the user.
- Sanitization: There is no evidence of validation, escaping, or filtering of the external specification content before it is interpolated into the planning workflow.
Audit Metadata