ClawHub
Back to skill

Security audit

Nylas

Security checks across malware telemetry and agentic risk

Overview

This appears to be a read-oriented Nylas connector skill, with a broad activation phrase that users should understand but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you want an agent to read data from your connected Nylas account. Treat calendar and grant information as sensitive, and confirm the specific account, calendar, and date range before asking the agent to retrieve data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description says to use this skill for "ANY Nylas request" and "instead of calling the API directly," which is an overly broad invocation rule that can cause the agent to route all Nylas-related tasks through this skill without evaluating whether the scope is appropriate. In context, the skill currently exposes read-oriented actions, but the broad trigger language could still cause overuse, accidental data access, or future unsafe behavior if more privileged actions are later added.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal