ClawHub
Back to skill

Security audit

GLM-V-Resume-Screen

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it screens resumes through Zhipu's external GLM-V API, so users should treat resume contents and the API key as sensitive.

Install only if you are allowed to send the resumes and screening criteria to Zhipu's API. Use a dedicated API key where possible, avoid putting unnecessary sensitive information in resumes, review provider data-handling terms for your use case, and save outputs only to locations appropriate for candidate data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation indicates access to environment variables, file output, and networked API calls, yet no explicit permission declaration is present in the skill metadata. This weakens transparency and permission gating, increasing the chance that users or hosting platforms invoke data-exfiltrating behavior without informed consent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill processes resumes, which commonly contain sensitive personal data, and sends their contents to an external model provider, but the user-facing description does not clearly warn about that transfer. This creates a privacy and compliance risk because users may disclose personal or regulated data without informed consent.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The tool sends resume contents, which commonly include sensitive personal data, to a third-party API without an explicit user-facing privacy warning or consent flow at the point of use. In the context of resume screening, this increases the risk of unintentional disclosure of PII to an external processor.

Session Persistence

Medium
Category
Rogue Agent
Content
This script reads the key from the `ZHIPU_API_KEY` environment variable and shares it with other Zhipu skills.
脚本通过 `ZHIPU_API_KEY` 环境变量获取密钥，与其他智谱技能共用同一个 key。

**Get Key / 获取 Key：** Visit [Zhipu Open Platform API Keys / 智谱开放平台 API Keys](https://bigmodel.cn/usercenter/proj-mgmt/apikeys) to create or copy your key.

**Setup options / 配置方式（任选一种）：**
Confidence
83% confidence
Finding
create or copy your key. **Setup options / 配置方式（任选一种）：** 1. **OpenClaw config (recommended) / OpenClaw 配置（推荐）：** Set in `openclaw.json` under `skills.entries.glmv-resume-screen.env`: ```json

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
> **Local PDF / 本地 PDF:** Local PDF files are converted page-by-page into images (base64) before sending to the model. `PyMuPDF` is required (`pip install PyMuPDF`). URL files support full formats including pdf/docx/txt.
> 本地 PDF 会自动逐页转为图片（base64）传给模型，需要安装 `PyMuPDF`（`pip install PyMuPDF`）。URL 文件支持 pdf/docx/txt 等全格式。

### 📋 Output Display Rules (MANDATORY)

After running the script, **you must display the complete screening result (Markdown table) exactly as returned**. Do not summarize, truncate, or only say "screening completed". Users need each candidate's detailed analysis to decide.
Confidence
97% confidence
Finding
Display Rules

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.