skills/zoom/skills/zoom-rest-api/Gen Agent Trust Hub

zoom-rest-api

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill's documentation for processing webhooks and recording data introduces an indirect prompt injection surface.
  • Ingestion points: Untrusted data from Zoom webhooks is processed in the provided Express.js server example in examples/webhook-server.md.
  • Boundary markers: Boundary markers or explicit instructions for the AI to ignore embedded commands are absent from the provided code samples.
  • Capability inventory: The skill provides instructions for extensive meeting and user management capabilities, which could be misused if malicious data is ingested (e.g., examples/meeting-lifecycle.md, examples/user-management.md).
  • Sanitization: The provided code snippets do not demonstrate content sanitization or validation of the external data being processed.
  • [EXTERNAL_DOWNLOADS]: The skill references several external packages and resources from well-known and trusted sources.
  • Recommends the installation of standard industry packages including express, body-parser, axios, and dotenv.
  • Mentions the official @zoom/rivet SDK for simplified API interaction.
  • References official OpenAPI specifications and sample repositories hosted by the Zoom organization on GitHub (github.com/zoom/api).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 05:25 PM