knowledge-graph

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external content from ServiceNow tables, which creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: The skill retrieves and analyzes the text field from the kb_knowledge table and metadata from the incident and label_entry tables in Step 3 to discover relationships.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific prompts to the agent to disregard instructions potentially embedded within the knowledge base content.
  • Capability inventory: The skill possesses write capabilities through the SN-Create-Record and SN-Update-Record tools and general processing capabilities via the Bash native tool.
  • Sanitization: Absent. There is no guidance provided for validating or sanitizing the content retrieved from ServiceNow before it is used to trigger subsequent database operations or tool executions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — knowledge-graph