The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection as it is designed to read and interpret project-specific documentation to drive code implementation and alignment.
Ingestion points: The agent reads content from various files in the docs/context/ directory, including PRD.md, APP_FLOW.md, TECH_STACK.md, FRONTEND_GUIDELINES.md, BACKEND_STRUCTURE.md, and IMPLEMENTATION_PLAN.md as defined in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings when processing the contents of these external documentation files.
Capability inventory: The skill is capable of reading and writing files within the restricted docs/context/ directory using host-managed interfaces.
Sanitization: The prompt instructions do not include explicit sanitization, escaping, or validation of the content read from the documentation files before it is processed by the agent.

context-architect