board-canon

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the runtime card body/PR content that this reference skill is consulted on (e.g., card comments naming blockers, PR body sections validated by enforcing-pr-contract), which are authored by non-operating users and are read as markdown prose for contract checks.