ClawHub
Back to skill

Security audit

LangSmith

Security checks across malware telemetry and agentic risk

Overview

This appears to be a LangSmith integration skill with a broad trigger phrase, but no artifact-backed evidence of hidden, destructive, or unrelated behavior.

Before installing, check that the skill asks before creating, updating, or deleting LangSmith resources, and use a least-privilege LangSmith token. The broad trigger wording is worth improving, but the available evidence supports benign classification rather than Review.

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
84% confidence
Finding
The phrase 'Use this skill for ANY LangSmith request' creates an overly broad trigger that can cause the agent to route all LangSmith-related tasks through this skill without meaningful scope checks. Because the skill includes both read and write actions, this broad invocation language increases the chance of unintended state-changing operations being selected or attempted in contexts where a narrower, read-only or task-specific skill would be safer.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.