ClawHub
Back to skill

Security audit

4chan-reader

Security checks across malware telemetry and agentic risk

Overview

This skill transparently fetches public 4chan catalog or thread content and can optionally save thread text to a user-chosen local folder.

Install only if you are comfortable with the agent fetching public 4chan pages. Treat all fetched or saved post text as untrusted forum content, and save thread dumps only to a dedicated non-sensitive folder.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill advertises and invokes code that performs network access and can write fetched content to local files, but no permissions are declared. That creates a transparency and policy gap: users and calling systems may not realize the skill can exfiltrate remote content into the local filesystem, increasing the chance of unsafe or unintended use.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The workflow notes that output can be saved, but it does not clearly warn users in the skill description or safety-facing metadata that thread content and file metadata may be persisted locally. This can lead to accidental storage of sensitive, offensive, or policy-relevant material on disk without informed user consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.