ad-pentest

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches reputable security tools from official GitHub repositories and package registries (PyPI, Go Proxy).
  • [COMMAND_EXECUTION]: Orchestrates a structured series of CLI-based security assessments against Active Directory infrastructure using Impacket, CrackMapExec, and Certipy.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: Processes output from network services (LDAP, Kerberos) via tools like ldapsearch, bloodhound-python, and certipy in SKILL.md.
  • Boundary markers: Untrusted tool output is integrated into the agent session without delimiters or explicit instructions to ignore embedded commands.
  • Capability inventory: Includes broad subprocess execution, network communication, and local filesystem writes.
  • Sanitization: No validation or escaping is applied to remote data before it is included in reports or processed in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:07 AM
Security Audit — agent-trust-hub — ad-pentest