ClawHub
Back to skill

Security audit

letcairn.work

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward guide for installing and using the Cairn project-management CLI, with ordinary global npm and local workspace persistence risks disclosed enough for a benign verdict.

Before installing, make sure you trust the cairn-work npm package and publisher, because npm install -g runs third-party package code and leaves a global CLI on the system. Review where cairn onboard will create the workspace and context files, and use execute autonomy only for tasks where deploy, publish, send, or similar side effects are explicitly intended.

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
91% confidence
Finding
The README suggests users can tell their agent "work on the API task" and the agent will pick it up, but it does not define the exact trigger scope, required context, or exclusion conditions. This phrase overlaps with ordinary conversation and could cause unintended invocation in systems that map natural-language utterances to skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.