hunt-xxe

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). This skill provides explicit, actionable exploitation guidance and ready-to-run XXE payloads (file exfiltration, OOB callbacks, SSRF to metadata, RCE chains), which enable clearly malicious attacks.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs attackers/testers to exfiltrate and "show" sensitive files and cloud credentials (e.g., /etc/passwd, IMDS JSON, .aws/credentials) as proof, and provides payloads/requests that would return those secrets, so an LLM following the skill would be expected to handle and potentially output secret values verbatim.