ClawHub
Back to skill

Security audit

research-logger

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it searches the web, finds a GIF, and creates a persistent research note, with no evidence of hidden or destructive behavior.

Reasonable to install if you want automated Bear research notes. Avoid using sensitive or proprietary topics unless you are comfortable sending them to the configured search/GIF services, and review generated notes because they may contain untrusted or inaccurate web content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends the user-provided topic to external services via web_search and later gifgrep without any notice, consent, or validation. If a user enters sensitive research subjects, proprietary terms, or personal data, that information is disclosed to third-party services, creating a real privacy leak even though the behavior appears intended for functionality.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script persists fetched web content and derived notes into Bear or a local markdown file without warning the user that potentially sensitive research topics, URLs, summaries, and extracted findings will be stored. This creates a confidentiality and retention risk because external or local note storage may be synced, backed up, or later accessed by others beyond the user's immediate session.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly states it will fetch web content, fill a template, and create a Bear note, but it does not warn users that untrusted external content will be persisted into their notes application. This can lead to unintended storage of misleading, sensitive, or prompt-injected content and reduces informed user consent before a write action occurs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.