Back to skill

Security audit

发布抖音短视频_无限

Security checks for vulnerabilities and agentic risk

Overview

This skill automates Douyin video upload settings, but it advertises publishing while its actual final step saves a draft instead.

Review this before installing if you expect actual publication: the skill appears designed to upload and prepare a Douyin video as a draft, not complete publishing. Use it only with a dedicated OpenClaw browser profile and confirm the final Douyin state yourself before relying on automation results.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill's title and purpose state that it publishes short videos, while later instructions explicitly prohibit publishing and require draft-saving only. This internal contradiction is dangerous because an orchestrating agent may select the skill for publication tasks and falsely report task completion, undermining trust, auditability, and control over content operations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill advertises that it will publish Douyin videos, but the actual workflow ends with saving a draft via '暂存离开' instead of publishing. This creates a deceptive mismatch between declared capability and real behavior, which can mislead downstream agents or users into believing content was posted when it was not, causing workflow integrity and automation reliability failures.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill description and all trigger phrases are written only in Chinese, and the instructions assume Chinese UI labels and Chinese-language interaction throughout. This imposes a specific language/locale behavior without any user opt-in or explicit justification that the skill is limited to Chinese-speaking users or the Chinese Douyin interface.

Content

No source excerpt is available for this finding.