conversation-evaluator

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted user-generated text from ServiceNow conversation logs.
  • Ingestion points: User messages are retrieved from the sys_cs_message table in Step 2 of the procedure.
  • Boundary markers: The instructions do not specify the use of boundary markers or clear delimiters to isolate the untrusted conversation content from the agent's evaluation instructions.
  • Capability inventory: The skill has access to the Bash native tool and several ServiceNow modification tools (SN-Update-Record and SN-Add-Work-Notes).
  • Sanitization: There is no evidence of message sanitization or filtering applied to the retrieved conversation message bodies before they are presented to the AI for evaluation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:23 PM
Security Audit — agent-trust-hub — conversation-evaluator