jira-integration

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches Jira issues and comments from a third-party Jira instance via MCP or direct REST calls (see "Fetch a Ticket" and "Fetch Comments" in SKILL.md) and requires the agent to read and act on user-generated ticket text (analyzing requirements, deciding transitions/comments), which exposes it to untrusted third-party content that could contain indirect prompt-injection.