ssti-jinja2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs extracting secrets (e.g., SECRET_KEY, DB URIs, file contents, creds) and returning/saving them as evidence and in the engagement summary, which requires the LLM to handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document contains explicit, actionable instructions for achieving server-side template injection leading to remote code execution, credential and secret exfiltration, remote callbacks to attacker-controlled hosts, and multiple obfuscation/backdoor techniques—clear malicious intent and abuse patterns.