hunt-ssti

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive how-to for exploiting server-side template injection (SSTI) with concrete RCE, file- and metadata-exfiltration, and OOB callback payloads — clearly intended for malicious abuse.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow in SKILL.md is an SSTI detection/escalation guide that instructs sending free-text probes (e.g., {{7*7}}...) into multiple attacker-controlled reflection points like email templates, PDF/report generators, CMS previews, and profile fields—i.e., outsider-authored text is intentionally ingested for template rendering before item selection.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill gives explicit, engine-specific payloads to achieve remote code execution and data exfiltration (e.g., os.popen('id'), reading /etc/passwd, curl/nslookup to COLLAB), directly encouraging actions that would compromise the host or target system.