ClawHub
Back to skill

Security audit

Bookmark Intelligence Free

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned for X bookmark archiving, but it asks users to extract and store sensitive X session cookies while giving incomplete and partly inconsistent privacy guidance.

Install only if you are comfortable handling X session cookies like passwords. Keep the .env file private, do not commit or share it, restrict file permissions, and consider rotating/revoking the session after use. Also treat the saved bookmark JSON files as private account-linked data.

SkillSpector

By NVIDIA
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 (4)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The documentation makes contradictory claims: it advertises 'no AI' and keyword-only analysis, yet declares an LLM API as required and later references Agent LLM service failures. This can mislead users about what data may be processed by external model infrastructure, undermining informed consent and causing unintended data exposure if bookmark content or metadata is routed through the platform LLM.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill asserts that credentials never leave the machine and that there is no third-party telemetry, but elsewhere admits communication with X and references required LLM service usage. These overbroad privacy assurances are unsafe because they can cause users to handle highly sensitive Twitter session cookies under false assumptions about disclosure boundaries and external processing.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The setup flow instructs users to extract and store X/Twitter auth_token and ct0 cookies, which are highly sensitive session credentials that can enable account access if exposed. Presenting this operational step without a strong upfront warning, least-privilege guidance, and handling safeguards materially increases the chance of credential theft, accidental disclosure, or insecure storage.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill writes tweet/bookmark contents and analysis results to local JSON files, but does not clearly warn users about persistence of potentially sensitive browsing interests, saved content, and metadata on disk. This creates a privacy risk if the machine is shared, backed up insecurely, indexed by other tools, or the directory is later synced or committed unintentionally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.