ClawHub
Back to skill

Security audit

公众号贴图 / 九宫格多图推送

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WeChat multi-image publishing workflow that uses expected image-generation and WeChat publishing credentials, with no evidence of hidden persistence or unrelated data access.

Install this only if you intend to run a Chinese-language WeChat content workflow and are comfortable giving the agent access to image-model and WeChat app credentials. Review the generated plan and images before allowing publication, and keep aws.env scoped to the accounts and API keys needed for this workflow.

A.I.G

By Tencent
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

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description lists triggers such as “做一组图”, “发几张图”, “不写正文发图”, and “只发图不写字”, which are common conversational phrases and not narrowly scoped to this specific skill. Although some routing guidance is provided, the trigger set remains broad enough to overlap with normal user requests and may invoke the skill unintentionally.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
This markdown file uses Chinese throughout and does not indicate that the skill is region-specific or that users may choose another language. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Vague Triggers

Low
Confidence
80% confidence
Finding
This manifest is in scope for vague-trigger review, and the description only broadly states the skill's capabilities without indicating when it should be invoked or what phrases should trigger it. The lack of explicit trigger scope or exclusion conditions could contribute to unintended activation in systems that rely on manifest text for routing.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The manifest description forces a single language presentation for the skill and does not offer any user opt-in or alternative language choice. Under the stated policy, language-specific behavior should either provide choice or clearly document a justified locale constraint.

Credential Access

High
Category
Privilege Escalation
Content
- WECHAT_1_APPSECRET
      bins:
        - python3
    primaryEnv: aws.env
---

# 贴图 / 多图推送
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.