concept-extractor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The template includes an explicit instruction to start agents with mode: "bypassPermissions", which attempts to override permission/security controls and is unnecessary for concept extraction, so it is a deceptive instruction outside the skill's stated purpose.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt explicitly includes an Agent template with mode: "bypassPermissions", which directs the agent to bypass security/permission controls (a clear instruction to evade system protections), even though it doesn't request sudo or user creation elsewhere.