hunt-xxe

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs exfiltrating sensitive files and AWS IMDS responses and requires showing file contents or a single reproducible curl that demonstrates those secrets as proof, which would force an 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 exploit payloads and step-by-step instructions for XXE-based data exfiltration, SSRF to cloud metadata, credential theft, and paths to remote code execution — enabling deliberate malicious abuse.