ClawHub

Deepseek Extract

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed DeepSeek shared-chat exporter that writes a local transcript, with privacy cautions users should understand before use.

Install only if you intend to export DeepSeek shared chats you are authorized to access. Treat generated Markdown or JSON files as potentially sensitive, avoid storing them in shared or synced locations unless appropriate, and consider using a virtual environment for the Playwright install.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly writes extracted conversation data to an output file and also instructs cleanup of temporary files, yet it declares no permissions. That mismatch can bypass user expectations and policy controls around filesystem access, especially because the extracted content may contain sensitive conversation data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly promotes extracting and saving entire DeepSeek conversations but does not warn users that shared chats may contain sensitive personal, business, or credential-like data. In a data-extraction skill, omission of privacy guidance materially increases the chance of over-collection, unsafe storage, and unintended redistribution of conversation contents.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow tells the agent to launch Playwright against a DeepSeek share URL but does not clearly warn the user that this will open a browser session and send the URL and resulting page requests/content to DeepSeek. Because the skill handles full conversation extraction, this omission can cause users to unknowingly trigger network access involving potentially sensitive chat contents.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal