The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides an extensive collection of commands for network scanning, service enumeration, and exploitation of Kerberos services. Tools include nmap, nslookup, ldapsearch, and specialized security suites such as Impacket (GetNPUsers.py, GetUserSPNs.py, secretsdump.py), Rubeus, and Kerbrute. These operations are aligned with the skill's primary purpose as a penetration testing resource.
[EXTERNAL_DOWNLOADS]: The documentation includes instructions for installing security tools via standard package managers (pip install impacket, netexec, crackmapexec) and references official GitHub repositories for kerbrute, Rubeus, and pykek. These downloads target well-known open-source security projects.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill instructs the agent to process output from various external tools, such as nmap service scans and kerbrute user enumeration results (e.g., in SKILL.md Phase 2.1).
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the tool outputs provided in the methodology.
Capability inventory: The skill has broad capabilities including file system modification (writing to /etc/krb5.conf), network scanning, and complex command execution via multiple penetration testing frameworks.
Sanitization: The skill lacks explicit sanitization or validation logic for the data ingested from external tool outputs before it is used to inform subsequent agent actions.

kerberos-pentesting