The Agent Skills Directory

[COMMAND_EXECUTION]: Several Python scripts including adcs_esc_finder.py, kerberoast_audit.py, and rbcd_takeover.py utilize subprocess.run to execute external security utilities. This functionality is the intended design for providing a management interface for command-line based penetration testing tools.\n- [PRIVILEGE_ESCALATION]: The skill documentation and accompanying scripts facilitate privilege escalation within Windows Active Directory environments. This includes auditing OU permissions for delegated Managed Service Account (dMSA) creation via Get-BadSuccessorOUPermissions.ps1 and orchestrating NTLM relay attacks through coerce_relay_chain.sh.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Active Directory environments and the output of various security tools. The ingestion of this untrusted external data represents a potential surface for indirect prompt injection, which is a common risk for agents handling system discovery information.

active-directory-attack