The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous Bash command templates for performing security assessments in Active Directory environments. These templates utilize well-known open-source security tools such as the Impacket suite, Certipy, BloodHound-python, and CrackMapExec to identify and demonstrate potential misconfigurations. The use of variables like '$PASS' and '$USER' indicates these are intended for interactive use by a security professional.
[INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting data from Active Directory environments via LDAP and BloodHound collection tools. This ingestion of external data constitutes a potential surface for indirect prompt injection (e.g., malicious data embedded in AD attributes); however, this is a known risk factor associated with the primary functional purpose of security auditing tools and is addressed by standard professional usage practices.

ad-attacks