ClawHub
Back to skill

Security audit

Weixin Video Publish

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple guide for publishing a user-selected video to WeChat Channels and does not include hidden code, persistence, or unrelated access.

Install only if you want the agent to help publish videos through your logged-in WeChat Channels account. Before clicking publish, verify the account, video path, title, description, originality declaration, location, and whether visibility is friends-only or public.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description explains the publishing mechanics but does not clearly warn that the skill can post content publicly or with chosen visibility on the user's behalf using an already logged-in WeChat account. In this context, missing disclosure is more dangerous because the skill automates a sensitive external side effect—publication to a social platform—which can cause reputational damage, privacy leakage, or unintended public distribution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation phrase "帮我发布视频到视频号" is broad enough to plausibly match ordinary user requests to publish a video, which increases the chance of accidental or unexpected skill activation. Because this skill performs a real-world publishing action through browser automation, ambiguous triggering is risky and could cause unintended content posting under the user's logged-in account.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.