task-details

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

• Third-party content exposure detected (medium risk: 0.30). Skill runtime ingests Jira issue text (e.g., issue.fields.description, issue.fields.summary, and issue links returned by mcp.atlassian.getIssue(...)/searchIssues(...)) to extract acceptance criteria and dependencies, and these are outsider-authored via Jira submissions.