submit-pr

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and uses content from a Linear issue via get_issue(id) (title, description, acceptance criteria), which is user-generated third-party content that the agent reads and uses to construct PR titles/bodies and drive actions—allowing malicious instructions in the issue to influence behavior.