The Agent Skills Directory

[SAFE]: No malicious code or security threats were identified. The skill acts as a structured template generator for engineering documentation.\n- [PROMPT_INJECTION]: The skill exhibits an inherent surface for Indirect Prompt Injection (Category 8) because it processes external specifications and context files to generate plans. This is a characteristic of planning agents rather than a malicious defect.\n
Ingestion points: Input specifications provided via the --spec parameter and project context files provided via --context-files.\n
Boundary markers: No explicit delimiters or instructions are used to separate untrusted specification data from the system instructions.\n
Capability inventory: The skill writes generated plans to the docs/plans/ directory and generates instructions intended for downstream execution agents (superpowers:subagent-driven-development, superpowers:executing-plans).\n
Sanitization: The skill does not perform sanitization or validation on the content of the provided specifications.

writing-plans