hunt-ssrf

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive SSRF playbook containing actionable exploit payloads (cloud metadata token theft), exfiltration techniques, and RCE chains (gopher→Redis), indicating deliberate malicious intent and high abuse risk.

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

• Third-party content exposure detected (medium risk: 0.30). The skill describes SSRF hunting workflows that submit attacker-controlled text (e.g., url=... / source= / endpoint= parameters) to URL-preview/fetch/import/proxy endpoints for the victim to fetch server-side, so outsider-authored free text is ingested at runtime without selecting a specific trusted item.