ClawHub
Back to skill

Security audit

ScraperAPI

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a normal ScraperAPI helper, with one scoping note about broad activation wording but no evidence of hidden or harmful behavior.

Install only if you intend the agent to help with ScraperAPI tasks. Because the trigger wording is broad, review actions before the agent sends requests to ScraperAPI, especially any action that submits URLs or uses account credentials.

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 skill description says to use this skill for ANY ScraperAPI request and whenever a task involves ScraperAPI, which is an unusually broad invocation trigger. This can cause the agent to select the skill based on loose keyword matches rather than user intent, leading to unnecessary external requests or use of a write-capable integration in situations where direct guidance or a safer path would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.