ClawHub
Back to skill

Security audit

Web Search

Security checks across malware telemetry and agentic risk

Overview

This is a coherent web-search skill that relies on an external authenticated CLI and third-party search services, with cautions but no hidden or destructive behavior in the artifact.

Install only if you trust the inference.sh CLI and are comfortable sending searches, URLs, and extracted content to external providers. Prefer the manual checksum verification path, review infsh commands before approving them, and avoid submitting secrets, private internal URLs, regulated data, or proprietary content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description embeds many broad trigger phrases such as 'research', 'agents', 'internet search', and 'content extraction', which are likely to match ordinary user requests and cause this skill to activate too often. In a skill that can send user queries to external services and invoke Bash commands, overbroad triggering increases the chance of unintended tool use and unnecessary disclosure of user input.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill describes web search and extraction behavior but does not clearly warn that prompts, search queries, and supplied URLs will be transmitted to third-party services such as inference.sh, Tavily, and Exa. Because the skill is intended for research and agent workflows, users may provide sensitive internal questions, URLs, or data without realizing that this information leaves the local environment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal