ClawHub
Back to skill

Security audit

AnyCrawl-API

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward AnyCrawl API wrapper, with normal cautions around third-party web crawling and API-key handling.

Install this only if you intend to use AnyCrawl. Use a revocable API key, avoid submitting private URLs, internal endpoints, secrets, or confidential content unless approved, keep crawl limits narrow, and store the API key in a trusted secret mechanism rather than synced or shared dotfiles.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README promotes web scraping, crawling, and search against third-party sites but does not warn users that their queries and target URLs are sent to an external service and may trigger requests against third-party systems. In an agent skill context, this omission can lead to unintended data disclosure, policy violations, or abusive traffic because users may invoke these functions without understanding the external network effects.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill exposes scraping, search, and crawl functions that send user-provided URLs, queries, and page content to the external AnyCrawl service, but the description does not warn users about this data flow. This can cause unintentional disclosure of sensitive URLs, internal endpoints, search terms, or scraped content to a third party when users assume processing is local.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The setup instructions tell users to persist an API key in shell startup files without warning about local credential exposure risks. Storing secrets in ~/.bashrc or ~/.zshrc can leak them through backups, dotfile sync, shared accounts, screenshots, shell history mistakes, or overly broad file permissions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
index.js:6