ClawHub
Back to skill

Security audit

defuddle-web-cleaner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward webpage-to-readable-content helper, with expected network access when given URLs and no evidence of hidden execution, persistence, credential use, or destructive behavior.

Install only if you want an agent to clean webpages into readable article text or markdown. Treat URL input as permission for the agent or Defuddle tooling to fetch that page, and avoid using private intranet URLs, authenticated pages, or sensitive documents unless you are comfortable with that retrieval path.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broad enough to trigger on many common URL, HTML, scraping, research, and markdown-conversion requests, which increases the chance of overbroad invocation. This can cause the agent to fetch or process web content in situations where the user did not explicitly ask for remote retrieval or this specific tool, creating unnecessary exposure to untrusted content and unintended network actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states it supports URL input and includes a step to load page HTML, but it does not warn that using a URL may trigger remote content fetching. This reduces transparency and can lead to unexpected access of attacker-controlled or sensitive URLs, increasing risks such as SSRF-like behavior, retrieval of malicious content, or violating user expectations about network access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.