ClawHub
Back to skill

Security audit

Scrape.do

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Scrape.do connector helper that uses OOMOL's CLI for read-oriented scraping actions and does not show hidden or destructive behavior.

Install this only if you are comfortable using OOMOL's oo CLI and connecting your Scrape.do account through OOMOL. Review the remote CLI installer before first-time setup, and remember that scraping target sites may have legal or terms-of-service limits even though the skill itself is read-oriented.

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
89% confidence
Finding
The manifest description says to use this skill for "ANY Scrape.do request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to route all Scrape.do-related tasks through this skill without sufficient task-level scrutiny. Broad invocation guidance increases the chance the skill is selected in inappropriate contexts and exposes users to the skill's embedded operational instructions, including setup commands, even when a narrower or safer path would suffice.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.