hunt-prototype-pollution

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive guide describing prototype pollution attacks and provides concrete exploit payloads and gadget chains to achieve RCE, XSS, auth bypass, and persistence, indicating clear malicious intent and abuse capability.

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

• Third-party content exposure detected (medium risk: 0.30). The skill is a static procedure showing how an outsider can send crafted payloads (e.g., query params/JSON bodies via curl) into application request handlers that merge untrusted properties, which would expose the agent’s runtime to outsider-authored free text being ingested by the monitored workflow.