openclaw-traffic-guardian

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

• Third-party content exposure detected (high risk: 0.90). The skill's SPEC.md and SKILL.md explicitly require inspecting agent HTTP/HTTPS request and response text via a process-scoped proxy / optional HTTPS MITM (observing "agent HTTP/HTTPS traffic" and "inspect HTTP request/response text"), which means it will ingest untrusted third-party web content that could contain instruction-like payloads influencing detections or subsequent actions.