Toutiao Graphic Publisher

Security checks across malware telemetry and agentic risk

Overview

This skill matches its stated purpose, but it can automatically publish real Toutiao posts without a clear final approval step.

Install only if you intend to let an agent operate a logged-in Toutiao publishing account. Before use, require a manual preview and explicit final approval of the title, body, tags, and target account, and be especially cautious with batch publishing because mistakes could become public posts.

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
94% confidence
Finding
The trigger section includes broad behavioral conditions such as a user having content to publish or needing batch publishing, not just explicit invocation phrases. This increases the chance the skill activates during ordinary conversation and performs high-impact browser automation on a real publishing account without sufficiently clear user intent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill is designed to carry the workflow through to 'Confirm Publish' automatically, but it does not require an explicit user confirmation immediately before the irreversible publishing action. In the context of a real content platform account, this can cause unintended public posting, reputational harm, and accidental publication of sensitive or non-compliant material.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal