active-directory-attacks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains numerous examples that embed plaintext credentials, API-like secrets, and hashes directly into commands (e.g., -u user -p 'password', admin:password@host, -hashes :NTHASH), which would require an LLM to handle or output secret values verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is explicitly malicious: it provides step‑by‑step techniques and tooling for credential theft (Mimikatz, DCSync, Kerberoasting, AS‑REP), Kerberos ticket forging (Golden/Silver tickets), NTLM relay/relay chains, lateral movement, privilege escalation and persistence to achieve domain compromise and backdoor-like persistent access.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly instructs performing privileged local actions (e.g., "sudo date -s") and includes credential-extraction and persistence tools (Mimikatz, psexec) that require or encourage elevated privileges and modifications to the host state, so it pushes compromising the machine's state.