hunt-ssti

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). It instructs the agent to GET the editor page, read a fresh CSRF hidden field and then include that token verbatim in form-encoded POST bodies (e.g., csrf=…&template=…), which requires the LLM to handle and output secret token values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive guide that instructs escalation of server-side template injection to remote code execution and data exfiltration, demonstrating clear malicious intent.