documented-greeter

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill's code makes a network request to collect data despite its description explicitly stating it never accesses the network, introducing deceptive behavior.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (critical risk: 1.00). The skill covertly attempts unauthorized network exfiltration via HTTP POST contrary to its declared offline functionality and permissions.