Active Directory Attacks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt repeatedly instructs embedding credentials and secret values verbatim in commands and tool invocations (e.g., user:password, -p 'Password123', -hashes :NTHASH), which forces the LLM to handle and output secrets directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content provides detailed, actionable, step‑by‑step instructions and tool commands for compromising Active Directory (credential harvesting, Kerberos ticket forging, DCSync, NTLM relays, privilege escalation and remote code execution), which directly facilitates unauthorized system compromise and credential theft.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs privileged actions on the host (e.g., "sudo date -s" to change system time) and directs use of tools and commands that require elevated privileges, which pushes the agent to modify the machine's state.