helpdesk-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): Detected a potential surface for indirect prompt injection.
  • Ingestion points: The tool HELPDESK_LIST_TICKETS retrieves data from external helpdesk tickets which could contain malicious instructions.
  • Boundary markers: No specific delimiters or "ignore" instructions are defined for the ingested data to prevent the agent from following embedded commands.
  • Capability inventory: All listed tools (HELPDESK_LIST_TICKETS, HELPDESK_LIST_VIEWS, HELPDESK_LIST_CANNED_RESPONSES, HELPDESK_LIST_CUSTOM_FIELDS) are read-only listing operations.
  • Sanitization: No sanitization or validation of the external ticket data is performed or instructed.
  • No Code (SAFE): This skill consists of documentation and configuration metadata only. No executable scripts, binaries, or automated installation steps are present in the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:19 AM