ClawHub
Back to skill

Security audit

Context7

Security checks across malware telemetry and agentic risk

Overview

This is a focused Context7 documentation connector with disclosed external account use and no hidden or destructive behavior found.

Install this if you want Codex to use your OOMOL-connected Context7 account for documentation lookup. Avoid using it for sensitive private queries unless you are comfortable sending that query context through the OOMOL/Context7 connector, and review the oo CLI setup before running first-time installation or login steps.

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
95% confidence
Finding
The trigger text is overly broad because it instructs the agent to use this skill for ANY request that merely involves Context7, rather than scoping invocation to specific user intents or operations. This can cause unintended routing, overuse of an external connector, and accidental disclosure of user queries or context to the Context7 service when a narrower or direct handling path would have been more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.