worker

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

• Third-party content exposure detected (high risk: 0.90). The worker explicitly polls external ticket providers (see "Poll — Fetch ready tickets from the configured provider" and the Supported Providers list in SKILL.md: clickup, github, linear, jira), ingesting user-generated ticket descriptions that the agent reads and uses to plan and execute code and PRs, so untrusted third-party content could inject instructions.