skills/nylas/skills/nylas-api/Gen Agent Trust Hub

nylas-api

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference and integration guide for the Nylas v3 API. It contains no executable code or automated scripts.
  • [EXTERNAL_DOWNLOADS]: Mentions official Nylas SDKs available through standard package registries (npm, pip, gem). These are verified vendor resources from nylas.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains extensive security instructions in rules/security-untrusted-content.md and AGENTS.md that explicitly warn the agent to treat data from emails, attachments, and meeting transcripts as untrusted content and to require user confirmation before performing any mutations. This follows best practices for mitigating indirect prompt injection.
  • [COMMAND_EXECUTION]: Provides standard curl examples for API interaction. These examples use placeholders for sensitive values like API keys and grant IDs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 11:06 PM
Security Audit — agent-trust-hub — nylas-api