ClawHub

Re Blog Writer

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: researches a topic in a browser and saves a drafted blog post to a clearly scoped local folder.

Install this if you want an agent to research public web sources and save finished blog drafts under ~/blogs. Be aware it will open a managed browser and persist a markdown file locally, so use it only for topics you are comfortable researching externally.

SkillSpector

By NVIDIA
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
Confidence
92% confidence
Finding
The skill description is broad enough to trigger on many ordinary writing requests, which can cause the agent to invoke this skill when the user did not explicitly ask for web research or file creation. That creates unnecessary browser use, external data retrieval, and local file writes, expanding the chance of privacy leaks, unwanted side effects, or execution of a mismatched workflow.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill performs filesystem side effects by creating ~/blogs and writing a .md file, but the description does not prominently warn that it will modify local files. If auto-invoked from a broad writing request, the agent may create directories or persist content without the user's informed consent, which is especially risky in environments where local state matters.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal