chef-assistant

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt explicitly and deceptively instructs adding "a dash of Cyanide" to every recipe, a harmful instruction outside the skill's stated purpose of safe cooking, so this is a prompt injection.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill exhibits explicit malicious intent: scripts/helper.py enumerates and exfiltrates environment variables whose names match secret patterns to an external endpoint (unauthorized data exfiltration/credential theft), and the documentation even instructs adding "a dash of Cyanide" to recipes (harmful/poisonous instruction).