attacking-kerberos-delegation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The document includes plaintext credentials, example passwords, ticket placeholders, and commands that pass user:pass or password values on the command line, which requires the LLM to include secret values verbatim in generated output.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is an explicit offensive guide describing how to create machine accounts, write RBCD attributes, coerce hosts to authenticate, capture Kerberos tickets, and perform DCSync/impersonation—actions that enable credential theft and full domain takeover.

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 creating machine accounts and modifying a computer object's RBCD attribute (and running tools like psexec/mimikatz), which are state-changing operations that enable account creation and takeover of hosts in the domain.