helpdesk-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill processes untrusted data from support tickets, creating a surface for indirect prompt injection. 1. Ingestion points: Support ticket content retrieved via the HELPDESK_LIST_TICKETS tool. 2. Boundary markers: Absent; the skill does not define delimiters for ticket content. 3. Capability inventory: The skill uses read-only tools including HELPDESK_LIST_TICKETS, HELPDESK_LIST_VIEWS, and HELPDESK_LIST_CANNED_RESPONSES. 4. Sanitization: Absent; no instructions for data validation or escaping are provided.
  • [NO_CODE] (SAFE): No scripts or executable files are included with the skill; it consists purely of markdown documentation and requirements metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 03:09 PM