ClawHub
Back to skill

Security audit

boss-geek

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed BOSS直聘 job-search helper, but some commands can send real messages from the user’s logged-in account.

Install only if you are comfortable letting the referenced OpenCLI plugin use your logged-in BOSS直聘 browser session. Review the external plugin source before installing, consider using a separate Chrome profile, and manually verify the recipient, job, and exact message before running greet or send.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly advertises actions that can contact HR on the user's behalf, but it does not clearly warn that these are external, account-linked communications that may be irreversible or socially consequential. Because it reuses an authenticated Chrome session on zhipin.com, invoking these commands can send real messages from the user's account and create unintended outreach if the user misunderstands the automation.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The workflow examples normalize sending greetings and replies as routine steps without any caution that these commands transmit messages to third parties and may not be undoable. In this context, the examples increase the chance of accidental or impulsive outbound communication from the user's real job-seeking account, which can affect reputation, employer interactions, and account trust.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.