competition-ssrf-metadata-pivot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to record and "preserve" extracted tokens/credential fields and to map token extraction and replay paths, which requires handling secret values verbatim in outputs (high exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly guides using SSRF to reach internal/metadata endpoints, extract tokens/credentials, and replay them against downstream services — i.e., deliberate credential theft and data exfiltration capability.