gap-grouping
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external ServiceNow tables to generate reports and action plans.
- Ingestion points: Processes user-generated content from
incident.close_notes,search_log.search_term,kb_feedback.comments, andkb_submission.description(SKILL.md, Steps 1-4). - Boundary markers: Lacks explicit delimiters or instructions to ignore potential commands embedded in the processed data during the clustering and creation phases.
- Capability inventory: Includes write operations to the ServiceNow instance via
SN-Create-Record,SN-Update-Record, andSN-Add-Work-Notestools (SKILL.md, Step 9). - Sanitization: No sanitization or validation steps are defined for external content before it is interpolated into summaries or new records.
Audit Metadata