itsm-chat-reply-recommendation

Warn

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes and demonstrates the SN-Execute-Background-Script tool within the ServiceNow environment. This tool enables the execution of arbitrary JavaScript code on the platform, representing a high-privilege capability that could be misused if the agent is manipulated.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it retrieves and processes data from untrusted sources like incident descriptions and chat histories.
  • Ingestion points: Retrieval of incident and interaction table records in SKILL.md.
  • Boundary markers: The prompt templates used to generate recommendations do not include delimiters or protective instructions to isolate untrusted user data.
  • Capability inventory: The skill utilizes high-privilege tools such as SN-Update-Record and SN-Execute-Background-Script which could be targetted by an injection attack.
  • Sanitization: There is no evidence of input validation or sanitization before external data is interpolated into the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — itsm-chat-reply-recommendation