work-order-summarization
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external ServiceNow tables for summarization, which is an architectural surface for indirect prompt injection. However, as this is the primary purpose of the skill and no malicious content is present, it is considered safe.
- Ingestion points: ServiceNow records retrieved through tool calls to tables like wm_order and wm_task.
- Boundary markers: None identified in the summary template.
- Capability inventory: The skill uses MCP and Bash-based REST tools to query database records.
- Sanitization: Standard processing of database fields without additional filtering instructions.
Audit Metadata