jira-issue-to-pr

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

• Third-party content exposure detected (high risk: 0.90). This skill polls Jira Cloud issues and extracts outsider-authored ticket description (and other ticket fields like summary/key) into a runtime-created prompt, which is then sent as initial_message to the agent LLM via POST /api/conversations.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The automation's runtime prompt tells the spawned agent to clone the target GitHub repository specified in Jira tickets (e.g. https://github.com// and https://github.com/acme-org/backend), so arbitrary remote repository content will be fetched at runtime and can influence/contain executable code.