skills/vm0-ai/vm0-skills/zapier/Gen Agent Trust Hub

zapier

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes curl for API interactions, representing standard and documented usage for the service.\n- [EXTERNAL_DOWNLOADS]: Communication is restricted to actions.zapier.com, the official domain of Zapier, which is a well-known technology company and automation service.\n- [PROMPT_INJECTION]: The skill features an indirect prompt injection surface due to its natural language command interface for automation.\n
  • Ingestion points: The instructions parameter in API request bodies within SKILL.md.\n
  • Boundary markers: Delimiters are absent from the instruction templates.\n
  • Capability inventory: Orchestrates actions across various connected third-party services via Zapier AI Actions.\n
  • Sanitization: Input processing and safety checks are deferred to the Zapier AI Actions API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:44 PM