The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, untrusted project files which could potentially contain malicious instructions designed to influence the agent's output.
Ingestion points: The skill reads data from task-###.md, prd.md, explore.md, intent.md, and CHAIN-OF-TRUTH.md files found within the .lcs/ directory structure (SKILL.md, Behavior checklist steps 2, 4, and 7).
Boundary markers: No explicit boundary markers or 'ignore' instructions are defined for the agent to distinguish between documentation content and potential instructions within the source files.
Capability inventory: The skill possesses the capability to read files, write new markdown documentation, create directories, and delete the source work-item folders (SKILL.md, Behavior checklist steps 5, 6, 7, 9, 10, and 11).
Sanitization: There is no mention of sanitization, validation, or escaping of the content extracted from the source files before it is formatted into the final doc.md and map.md artifacts.

lcs-doc-finalizer