vulnerability-verification

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These URLs include attacker-controlled domains/callback services, open-redirects and SSRF payloads (including direct requests to cloud metadata, file://, gopher://, and local IPs) which are high-risk vectors for credential theft, data exfiltration and hosting/triggering of malicious payloads.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). High-risk: the content contains explicit, actionable instructions for data exfiltration, credential theft (including SSRF to cloud metadata and cookie theft), and stealth/evasion techniques that enable abuse and post-compromise chaining.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for superhackers:vulnerability-verification ingests and searches free-text returned by attacker-controlled targets/HTTP responses at verification time (e.g., using curl/nuclei and then search_text/rg over the response body).