The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted markdown files (prd.md, prd-enhanced.md) to generate technical specifications. This creates an attack surface where instructions embedded within these source documents could influence the agent's behavior.
Ingestion points: The skill reads content from prd-enhanced.md, prd.md, and .lcs/state.md to drive its logic.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content of the source documents.
Capability inventory: The skill has the authority to write multiple new files to the filesystem (srs.md, api.md, db.md, tests.md, traceability.md).
Sanitization: The skill does not mention any sanitization or validation of the ingested text before processing it for output generation.

lcs-tosrs