unified-ticket-fetcher
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from Jira, Plane, and ServiceNow, creating a surface for indirect prompt injection attacks.
- Ingestion points: Ticket titles and descriptions fetched via API from external providers in
SKILL.md(Step 1 and Step 3). - Boundary markers: The instructions do not specify the use of clear delimiters or instructions to the agent to disregard embedded commands within the normalized task output.
- Capability inventory: The skill is part of a broader agent system that utilizes authentication and task tracking via
unified_task_tracker. - Sanitization: Step 3 mentions stripping platform-specific HTML/formatting, which is a standard data cleanup step but does not effectively filter out malicious natural language instructions.
Audit Metadata