The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data which could contain instructions to influence the agent's actions during the implementation phase.\n- Ingestion points: The skill reads external tickets, specifications (Spec), and Architectural Decision Records (ADR) as specified in SKILL.md.\n- Boundary markers: The skill includes explicit instructions to restrict the agent to session-provided materials and requires reporting INCOMPLETE if boundaries are vague.\n- Capability inventory: The skill is designed to perform file modifications and execute tests using the /tdd tool.\n- Sanitization: No explicit sanitization of document content is described in the provided files.

afk-worker