The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon project documentation and source code which could contain malicious instructions designed to influence the agent's behavior during implementation or verification steps.
Ingestion points: The workflow in SKILL.md explicitly instructs the agent to read docs/SUMMARY.md, Code Standard documents, and other task-relevant detail documents.
Boundary markers: There are no instructions for the agent to use delimiters or specific safety markers to distinguish between legitimate documentation and potential instructions embedded within that data.
Capability inventory: The skill has the capability to write to the local file system (Step 2: Implement) and execute commands for testing, linting, and building (Step 3: Verify).
Sanitization: The skill does not define any methods for sanitizing, validating, or filtering the content of the documentation files before they are processed by the agent.

quick-implement