The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous shell commands for LDAP enumeration and exploitation using tools like ldapsearch, nmap, netexec, hydra, and impacket.\n- [EXTERNAL_DOWNLOADS]: Instructions in SKILL.md and references/ldap-techniques.md specify installing the ldapdomaindump package via pip3 install, which fetches code from a public registry at runtime.\n- [DATA_EXFILTRATION]: The methodology directs the agent to search for and read sensitive system configuration files such as /etc/sssd/sssd.conf and /etc/nslcd.conf to extract cleartext LDAP credentials.\n- [DYNAMIC_EXECUTION]: Includes Python code snippets utilizing the ldap3 library for directory modifications, such as overwriting the sshPublicKey attribute.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external LDAP servers (e.g., ldapsearch output) without boundary markers or sanitization. This untrusted content is processed in a context where the agent has significant capabilities, including subprocess execution and file access.

ldap-pentesting