kimi-vl-integration-protocol

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly encodes image assets to Base64 and injects them into an OpenAI-compatible multi-modal message payload—representing clear potential for unauthorized data exfiltration of visual content to external model providers; I found no signs of obfuscated payloads, hidden eval/exec, remote shells, or credential-theft routines in the described design.