The Agent Skills Directory

[SAFE]: The skill follows a predictable workflow to generate markdown files in a specific directory. It does not perform network operations, execute arbitrary code, or access sensitive system files.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes user input ($ARGUMENTS) and scans local files for context. Ingestion points: user arguments and scanned file content. Boundary markers: absent. Capability inventory: writing markdown files to the backlog/plans/ directory. Sanitization: absent. The risk is negligible as the agent only generates document content.

quick-plan