active-directory-attacks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill repeatedly shows command examples that embed plaintext credentials, hashes, and tokens (e.g., user:password, --ldappassword, :NTHASH, /krbtgt:HASH), which requires the LLM to handle or produce secret values verbatim and thus poses high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is an explicit, high-risk Active Directory attack playbook with step‑by‑step instructions for credential theft, forging Kerberos tickets, lateral movement, and deploying persistent backdoors—clearly intended for offensive compromise.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly instructs running privileged system commands (e.g., "sudo date -s" and "net time /domain /set") and describes creating persistent access and machine accounts, which push the agent to change the host or target system state and obtain elevated privileges.