ClawHub

LinkedIn Post

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed LinkedIn posting helper; it can publish publicly through a logged-in browser, but that behavior matches its stated purpose and is gated by an explicit publish flag and approval instructions.

Install only if you are comfortable letting this skill control a browser profile already logged into LinkedIn. Use prepare-only mode first, confirm the exact text, link preview, and selected account, and approve --publish only when you want the post to go live.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly instructs use of shell commands, reads local files for post content and config, and relies on environment variables for authentication, yet it declares no permissions. This creates a capability-transparency gap: an agent or reviewer may treat the skill as lower risk than it is, while it can access secrets and perform browser-driven external actions against a logged-in LinkedIn session.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The code performs an external side effect—publishing a LinkedIn post—immediately when --publish is supplied, with no secondary confirmation, dry-run default, or interactive acknowledgment at the point of action. In an agent skill context, this is more dangerous because a mistaken invocation or prompt-manipulated workflow can cause unintended public posting from a logged-in account.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal