active-directory-certificate-services
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple security assessment tools including
certipy,Certify.exe,ldapsearch,ntlmrelayx.py, andPetitPotam.py. These tools are used to perform sensitive operations such as Active Directory enumeration, template modification, credential forgery, and NTLM relaying. - [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface by interpolating untrusted user data into shell-executed commands across both files. Maliciously crafted inputs for variables such as usernames or target hostnames could potentially lead to command injection.
- Ingestion points: User-supplied parameters for
user@domain.com,password,DC_IP,CA_HOST, andREQUEST_IDinSKILL.mdandADCS_ESC_MATRIX.md. - Boundary markers: None present to delimit user input from instructions.
- Capability inventory: Extensive subprocess execution capabilities for network-interacting and system-modifying CLI tools.
- Sanitization: No evidence of input validation, escaping, or filtering before interpolation into command strings.
Audit Metadata