ClawHub
Back to skill

Security audit

image_to_ppt

Security checks across malware telemetry and agentic risk

Overview

This skill converts a user-provided image to a PPT by uploading it to Scnet, which matches its stated purpose but requires care with sensitive files.

Install only if you are comfortable sending selected images to Scnet for cloud conversion. Do not use it for confidential, regulated, or private images unless your organization approves that data flow, and keep SCNET_API_BASE pointed at a trusted endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares capabilities that include environment access, local file reads, network access, and shell execution, but it does not declare any permissions or constraints. This creates an authorization gap where an agent or reviewer cannot easily assess or restrict what the skill is allowed to do, increasing the risk of unintended data access or command execution.

Description-Behavior Mismatch

Medium
Confidence
87% confidence
Finding
The documentation describes a general-purpose document conversion service, while the skill metadata claims a narrower image-to-PPT purpose. That scope mismatch can mislead integrators and reviewers about what the skill can actually send and process, increasing the risk of unintended file handling and policy bypass through broader-than-advertised capabilities.

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The documented API explicitly accepts PDF_TO_WORD and IMAGE_TO_WORD in addition to IMAGE_TO_PPT, which exceeds the declared skill purpose. In agent settings, hidden or under-declared capabilities are dangerous because they can be invoked to process more sensitive document types than users expect, including full PDFs and images unrelated to PPT generation.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The activation guidance is broad enough that an agent may invoke the skill whenever a user mentions converting an image to PPT, without strong validation of path source, file type, or user intent. Over-broad triggers can cause unintended execution on sensitive local files or send user data to an external service without sufficiently explicit consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The API accepts direct file uploads and public file URLs for processing by an external service, but the documentation does not clearly warn that user content is transmitted off-platform. This creates a privacy and data-governance risk, especially because documents and images may contain sensitive information and the service returns temporary external download links.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script uploads the user-supplied file to an external Scnet API, but the normal execution path only says it is 'submitting a conversion task' and does not clearly warn that file contents leave the local environment. In a skill context, users may assume local processing, so this creates a meaningful privacy and data-handling risk for sensitive images.

External Transmission

Medium
Category
Data Exfiltration
Content
SCNET_API_KEY=your_scnet_api_key_here

# API 基础地址（一般无需修改）
SCNET_API_BASE=https://api.scnet.cn/api/llm/v1

# 轮询配置（可选）
SCNET_POLL_INTERVAL=5
Confidence
94% confidence
Finding
https://api.scnet.cn/

External Transmission

Medium
Category
Data Exfiltration
Content
| 变量名 | 默认值 | 说明 |
|--------|--------|------|
| SCNET_API_KEY | 必需 | Scnet API 密钥 |
| SCNET_API_BASE | https://api.scnet.cn/api/llm/v1 | API 基础地址（一般无需修改） |
| SCNET_POLL_INTERVAL | 5 | 轮询状态间隔（秒） |
| SCNET_MAX_POLL_TIME | 600 | 最大轮询等待时间（秒） |
Confidence
93% confidence
Finding
https://api.scnet.cn/

VirusTotal

50/50 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.