Latchkey

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  2.3.0+5

Overview

Latchkey is a disclosed but very broad credential-injecting API tool that can let an agent act across many services, so it needs careful review before use.

Install only if you trust the latchkey npm package and explicitly want an agent to make authenticated API calls for you. Configure one narrowly scoped service at a time, prefer read-only or least-privilege tokens, avoid production/admin/payment credentials unless necessary, and require confirmation before any write, delete, billing, public-posting, or permission-changing request.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill is intentionally framed for 'arbitrary' third-party and self-hosted HTTP APIs, which makes its invocation scope very broad. In an agent setting, this can cause the skill to be selected for generic web/API tasks and trigger authenticated outbound actions against many services, increasing the chance of unintended data access or side effects.

VirusTotal

65/65 vendors flagged this skill as clean.