skills/happy-technologies-llc/happy-platform-skills/itsm-chat-reply-recommendation/Gen Agent Trust Hub
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-Scripttool 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
incidentandinteractiontable 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-RecordandSN-Execute-Background-Scriptwhich 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