cache-attack

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly scans cached responses for "email|password|token|user|auth" and then prints the cached file contents (head -5), which will cause any discovered secrets or tokens to be output verbatim and thus creates an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The file is an explicit offensive guide describing step-by-step web cache poisoning and deception techniques to inject malicious content and extract sensitive data, enabling credential theft and mass abuse.