conducting-pass-the-ticket-attack

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates shell commands for ticket extraction and lateral movement using specialized security tools like Mimikatz and Rubeus. These are intended for authorized simulation activities.
  • [DATA_EXFILTRATION]: The scripts read local Windows event logs and Kerberos ticket files for analysis purposes. No network exfiltration or unauthorized data access was detected.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface in its processing of external data. 1. Ingestion points: Windows security logs (agent.py) and .kirbi ticket files (process.py). 2. Boundary markers: None identified in script outputs. 3. Capability inventory: Generation of commands for remote execution (psexec, smbexec) and file system manipulation. 4. Sanitization: Untrusted data from logs and tickets is extracted as raw strings and printed to the console without validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 06:46 PM