The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external specification documents (PRD and SDD) to generate implementation plans, creating an attack surface for indirect prompt injection.
Ingestion points: The workflow in SKILL.md (Step 1: Initialize Plan) explicitly instructs the agent to read specification documents from the specDirectory to understand requirements and design.
Boundary markers: There are no instructions or templates provided that use delimiters or explicit 'ignore embedded instructions' warnings when processing these external documents.
Capability inventory: The skill possesses file-writing capabilities (creating plan/README.md and plan/phase-N.md files) and initiates subsequent implementation workflows via status reports and user questions.
Sanitization: The skill lacks mechanisms for sanitizing, escaping, or validating the natural language content extracted from the external documents before incorporating it into the generated implementation plan.

specify-plan