writing-plans
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external specifications or requirements to generate implementation plans. These plans include executable shell commands (e.g.,
pytest,git) and Python code snippets. If the input specification contains malicious instructions disguised as requirements, they could be propagated into the plan's executable sections. - Ingestion points: The 'spec or requirements' processed by the agent when using this skill as defined in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the input data.
- Capability inventory: The skill involves writing files to the file system ('docs/plans/') and specifically instructs the agent to transition to sub-skills ('superpowers:executing-plans', 'superpowers:subagent-driven-development') that likely possess command execution and file modification capabilities.
- Sanitization: No sanitization or validation of the input specification is described.
Audit Metadata