ClawHub
Back to skill

Security audit

Toutiao Graphic Publisher

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can automatically publish public Toutiao articles from a logged-in account without a final user confirmation after formatting and tag changes.

Install only if you are comfortable letting the agent use your logged-in Toutiao account to format, tag, and publish articles automatically. Before use, ask the agent to stop at preview and require your explicit approval of the account, title, final body text, and tags before it clicks Confirm Publish.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill automates the final 'Preview and Publish' and repeated 'Confirm Publish' clicks without requiring an explicit, just-in-time user confirmation immediately before the irreversible publish action. In a browser automation context, this increases the risk of accidental or unintended public posting, especially if the generated formatting, tags, or article content are wrong or noncompliant.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The trigger section hard-codes activation examples in both Chinese and English, but the skill does not explain how language choice is determined or whether the user can control the interaction language. This can create ambiguity around language/locale behavior and may conflict with policies requiring user opt-in for language preferences.

Content

No source excerpt is available for this finding.