rhdh-jira-authoring

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

• Third-party content exposure detected (medium risk: 0.30). The skill /rhdh-jira-refine (via this pack’s references/grill.md and references/duplicates.md) ingests user-provided conversation text for field inference and sizing, and then ranks/returns duplicate candidates by reading Jira issue data through /rhdh-jira-api search—both are LLM-readable at runtime.