code-review

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to "fetch the intent" from a ticket key or PR URL and to run multi-layer lenses against PR diffs, which are user-generated/untrusted third‑party contents (PR pages/ticket descriptions and public repo diffs) that the agent must read and which can materially influence its decisions and actions.