wechat-claw-skill

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:21 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed WeChat article workflow with optional publishing, but users should review content carefully before using live WeChat account actions.

Install only if you intend to automate WeChat article preparation. Start with `--dry-run`, inspect the rendered HTML and draft, confirm the target account, and use `--create-draft` or `--publish` only after an explicit human review. Review the separate image-generation, search, and WeChat helper skills or scripts because this skill delegates live network and account operations to them.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill documents draft creation and publication as routine pipeline steps but does not require an explicit user confirmation checkpoint or warn about the consequences of accidental publication. In this context, the skill targets a real-world公众号 publishing workflow, so an agent following the instructions could publish unwanted, incorrect, or noncompliant content to a live audience.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documentation presents a command sequence that can create drafts and publish content to an external WeChat account, but it does not prominently warn that these flags trigger real networked side effects. In an agent-skill context, users or automated systems may treat README commands as safe examples, increasing the risk of unintended live publication, asset upload, or account actions when `--create-draft` and `--publish` are copied or invoked blindly.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README advertises a workflow that uploads images, creates drafts, and publishes to a WeChat public account, but it does not clearly warn users that content and assets may be transmitted to external services and may affect a live account. In an agent/skill context, missing disclosure increases the chance of unintended external actions, especially when users may treat documented commands as safe defaults.

Missing User Warnings

High

• Confidence: 95% confidence
• Finding: The example command includes --create-draft and --publish, which can create externally visible changes on a connected WeChat account, yet the documentation provides no adjacent warning about irreversible/account-affecting behavior. In an automation skill, a copy-pasted command can lead to unintended publication of AI-generated or unreviewed content, making this more dangerous than ordinary documentation omission.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The document shows a full publishing command sequence including `--create-draft` and `--publish` but does not explicitly warn that these flags can trigger real external actions against a WeChat account. In an agent-skill context, documentation often shapes automated behavior, so omission of a clear confirmation/safety warning increases the chance of unintended draft creation or publication.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation provides a ready-to-run publish pipeline example with `--create-draft` and `--publish`, but it does not explicitly warn that these flags perform real external actions against a WeChat public account. In an agent-skill context, that omission increases the risk of unintended live posting or account-side state changes when a user or agent copies the example verbatim.

VirusTotal

64/64 vendors flagged this skill as clean.