The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted specifications to generate task-oriented implementation plans for downstream execution by sub-agents.
Ingestion points: The skill ingests user-provided specifications and requirements as defined in the SKILL.md instructions.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore or isolate potential embedded prompts within the source specifications.
Capability inventory: The skill generates file-write operations (saving plans to docs/superpowers/plans/) and produces shell commands (Git operations and testing commands) designed for automated execution by the subagent-driven-development or executing-plans sub-skills.
Sanitization: There is no evidence of sanitization, validation, or escaping of the input content before it is interpolated into the executable steps of the generated plan.

writing-plans