writing-plans
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied specifications and requirements to generate detailed implementation plans containing executable Python code and shell commands (e.g.,
pytest,git commit). This behavior establishes an attack surface for indirect prompt injection where malicious instructions embedded in a specification could potentially influence the generated code or commands. - Ingestion points: The skill ingests untrusted data in the form of a 'spec or requirements' for a multi-step task (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' warnings to prevent the agent from following directives contained within the input specifications.
- Capability inventory: The generated output includes Python source code and shell commands intended for execution by other skills such as
superpowers:executing-plans. - Sanitization: There is no requirement for the agent to sanitize or validate the content of the external specifications before using them to generate the plan.
- [NO_CODE]: This skill consists entirely of markdown instructions and metadata for the AI agent; it does not include any standalone executable scripts or binaries.
Audit Metadata