ClawHub

Nango API Integration

Security checks across malware telemetry and agentic risk

Overview

This Nango integration skill is coherent, but it deserves review because it enables broad credential-backed access to many external services without strong scoping or write-action confirmation guidance.

Install only if you intend to use Nango as a broad integration layer. Use least-privilege OAuth scopes and test accounts where possible, keep NANGO_SECRET_KEY and provider keys out of prompts and logs, require explicit approval before any write, delete, financial, public-posting, CRM, or repository mutation, and revoke unused Nango/provider connections when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding
The skill clearly instructs users to use environment variables such as NANGO_SECRET_KEY, but the manifest does not declare corresponding permissions or capabilities. This creates a transparency and governance gap: an agent may access secrets at runtime without the user being clearly informed through the skill metadata, which is risky for a skill centered on authentication and external API access.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger phrases include broad terms like "api integration," "connect api," and "external api access," which can match many unrelated requests and cause the skill to activate in overly general contexts. Because this skill deals with OAuth, API keys, and outbound integrations, accidental invocation could steer users into credential-handling workflows or external data transmission when a narrower tool would have been more appropriate.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill provides detailed instructions for OAuth flows, API key storage, proxying requests, and MCP/API integration, but it does not present a prominent user-facing warning that secrets and user data may be transmitted to third-party services. In a skill designed to connect to 700+ external APIs, this omission increases the chance that users expose credentials or sensitive business data without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal