ClawHub
Back to skill

Security audit

Context.dev

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Context.dev integration for public-web retrieval and extraction, with appropriate credential handling and confirmation for mutating monitor or batch actions.

Before installing, understand that this skill may call Context.dev for live public-web tasks and consume API quota. Configure the API key only if you want the agent to use this service, and review broad crawl, monitor, or batch requests before approving them.

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
92% confidence
Finding
The trigger description is broad enough to match many generic research, scraping, extraction, and web-data tasks, including cases where the user did not explicitly request Context.dev. This can cause unintended invocation of a powerful network-enabled skill, increasing the chance of unnecessary external data access, surprise tool use, and accidental expansion of the agent’s action scope.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.