hunt-lfi

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

• Third-party content exposure detected (low risk: 0.10). The required workflow sends requests to the user-supplied target and reads the response bodies (content matches, timing/length deltas, base64-decoded source), which are arbitrary web content an outsider controls, but the agent must actively fetch them rather than having outsider text pushed into a monitored feed.