ClawHub
Back to skill

Security audit

Web Scraper as a Service

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed workflow for building and running web scrapers, with a notable but manageable caution around user-agent rotation and scraping authorization.

Use this only for websites you are authorized to scrape, review robots.txt and terms first, and inspect the generated Python before running it. Prefer an honest, project-identifying User-Agent and keep the generated scraper and outputs inside a dedicated workspace.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill directs the agent to fetch external URLs, generate code, run scrapers, and write multiple output files, but it does not require an upfront warning or explicit confirmation about network activity and filesystem changes. This can lead to surprising side effects, unintended outbound requests, and unauthorized local modifications in environments where the user did not clearly consent to those operations.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill gives conflicting identity guidance: it requires User-Agent rotation with browser impersonation strings while later stating the scraper should identify itself honestly. In practice, rotating generic browser User-Agents can conceal automation, undermine transparent identification, and encourage scraping behavior that bypasses site operator expectations or anti-abuse controls.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill simultaneously mandates User-Agent rotation and instructs the scraper to identify itself honestly, creating contradictory guidance that can normalize deceptive identity presentation. In the context of a scraping automation skill, this ambiguity is especially risky because it can be interpreted as permission to masquerade as ordinary browsers to avoid scrutiny or anti-bot controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.