rest-integration

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for fetching and processing data from external REST APIs, creating a potential attack surface.
  • Ingestion points: The code examples in SKILL.md demonstrate retrieving content from external sources via sn_ws.RESTMessageV2 and response.getBody().
  • Boundary markers: The instructions do not include boundary markers or explicit guidelines to treat external API responses as untrusted data when processed by the agent.
  • Capability inventory: The skill facilitates the use of snow_execute_script, which allows for server-side code execution within a ServiceNow instance.
  • Sanitization: The provided code snippets show direct parsing of JSON responses and logging to system logs (gs.info, gs.error) without demonstrating sanitization or validation of the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:16 PM
Security Audit — agent-trust-hub — rest-integration