sqlmap

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

• Third-party content exposure detected (low risk: 0.10). The required workflow runs sqlmap against a user-supplied target URL, so the agent ingests target-application responses and dumped database contents that an outsider could influence, but only after the agent chooses to fetch that specific target, which makes it an arbitrary-URL fetch rather than a feed outsiders can force into the workflow.