jira-integration

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path fetches Jira issue content authored by other users (e.g., via MCP jira_get_issue / jira_search or REST GET /rest/api/3/issue/{key} and .../search), and that returned free-form text (descriptions, comments, etc.) is ingested into the agent’s LLM context.