ClawHub
Back to skill

Security audit

Wechat Mp Draft

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed WeChat Official Account publishing helper, with one activation-scope caveat users should manage before posting.

Install only if you intend the agent to help prepare or publish WeChat Official Account content. Keep API keys and logged-in Chrome profiles scoped to the account you want to use, review generated drafts before submission, and require explicit confirmation before any publish or draft-upload step.

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 (1)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger phrases are broad enough to match common user requests such as writing WeChat articles or fixing title duplication, which can cause the skill to activate in contexts where the user did not explicitly intend draft publication behavior. In this skill, unintended activation matters because the workflow includes downstream content transformation, image generation, and API-backed publishing actions, increasing the chance of unintended external side effects.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:147