ClawHub
Back to skill

Security audit

Anthropic

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Anthropic connector that uses OOMOL's oo CLI, with some broad wording users should understand before relying on it automatically.

Install this only if you are comfortable using OOMOL as an intermediary for Anthropic requests. Review payloads before approving create_message calls because prompts may be sent to Anthropic/OOMOL and may consume account credits; avoid treating general Anthropic discussion or documentation questions as automatic connector actions.

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 skill description says to use this skill for ANY Anthropic request and instead of calling the API directly, which is an overly broad routing rule. That can cause the agent to invoke a shell-capable connector skill for loosely related tasks without sufficient narrowing, increasing the chance of unintended execution paths or unsafe writes when the user only mentioned Anthropic generally.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.