The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from multiple external files and tool outputs, creating a surface for indirect instructions to influence agent behavior.
Ingestion points: The skill reads docs/dev-agents/config.md, PRD.md, SPEC.md, ROADMAP.md, and other files in rules_dir. It also ingests data from the wkc-tracker tool.
Boundary markers: No explicit delimiters or boundary markers (e.g., XML tags or clear separators) are defined to isolate untrusted content from the agent's core instructions.
Capability inventory: The skill has the capability to write to the ROADMAP.md file, invoke the wkc-tracker milestone close command, and call the wkc-backlog skill.
Sanitization: There is no evidence of sanitization, escaping, or filtering applied to the external content before it is processed by the model.

wkc-plan