hunt-dispatch

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive red-team / WAPT orchestration script that directs fingerprinting, credential capture/use, and loading of attack modules (RCE, supply-chain, MFA bypass, etc.), indicating intentional malicious/offensive actions.

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md step 1 fingerprinting, the workflow ingests landing-page HTML/body content from user-supplied target hosts via `curl -sSL -D
• -o /tmp/fp_body "https://$H"and then LLM-readable text is extracted withgrep ... /tmp/fp_body`, so outsider-authored content from those hosts can influence subsequent skill loading.