lcs-tosrs

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow reads the existing .lcs/work-items/<...>/prd.md (outsider-authored PRD content category: “issues/PRs/wiki/discussion threads authored by outsiders” / “documents the operating user did not author themselves”), and then extracts features/business rules/roles from that prose into the LLM context for transformation.