memory-management

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt includes hidden/silent-capture behavior (e.g., "Automatic zero-config: picks up ANTHROPIC_API_KEY" and automatic hooks that capture session env/data without explicit user action), which amounts to deceptive/exfiltration instructions outside the stated memory-management purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill contains intentional data-exfiltration and credential-harvesting behavior (automatic hooks that send conversation transcripts and explicitly "pick up ANTHROPIC_API_KEY" to an external classification/store service, plus stealthy fallbacks and always-on capture), which constitutes deliberate malicious/abusive behavior.