ad-delegation-abuse
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an educational reference detailing well-known Kerberos delegation attack vectors, including Unconstrained, Constrained (S4U), and Resource-Based Constrained Delegation (RBCD).
- [SAFE]: The referenced tools (Rubeus, Impacket, BloodHound, NetExec, and Certipy) are industry-standard for the described penetration testing use case and are correctly declared in the skill metadata.
- [SAFE]: No evidence of prompt injection, obfuscation, persistence mechanisms, or unauthorized network activity was found within the instructions.
- [SAFE]: The skill mentions commands for relaying NTLM to LDAP, but these are provided as instructional examples for security testing rather than automated malicious scripts.
Audit Metadata