SiliconFlow Qwen Vision

• Outcome: Pass
• Latest audit: May 29, 2026, 8:19 PM
• Version:
  0.2.0

Overview

This skill does what it claims: it sends a user-chosen image and prompt to SiliconFlow for vision analysis, with no hidden persistence or unrelated behavior found.

Install only if you are comfortable sending selected images and prompts to SiliconFlow. Avoid private screenshots, documents, faces, or regulated content unless external processing is approved, and prefer an environment variable or secret manager over typing API keys directly on the command line.

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 (4)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The README instructs users to analyze images using a third-party SiliconFlow/Qwen2.5-VL API and explains how to provide an API key, but it does not clearly warn that image contents and prompts will be transmitted to an external service. This can cause accidental disclosure of sensitive images or metadata, especially because the skill is explicitly for image understanding and users may submit private photos, documents, or screenshots.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill sends user-supplied images and prompts to an external SiliconFlow-hosted model, but the documentation does not clearly warn users that their content leaves the local environment. This can cause unintentional disclosure of sensitive images, embedded metadata, or confidential prompt content to a third party, especially in enterprise or regulated contexts.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The script base64-encodes the user-supplied image and transmits it to a third-party API, but the CLI does not provide a clear, explicit user-facing warning that local image contents will leave the machine. This matters because images may contain sensitive visual data or embedded metadata, and users may assume local-only processing from the skill description.

External Transmission

Medium

• Category: Data Exfiltration

Content

"max_tokens": 2048
    }
    
    response = requests.post(url, headers=headers, json=payload, timeout=120)
    
    if response.status_code != 200:
        print(f"Error: API 返回错误 {response.status_code}", file=sys.stderr)

• Confidence: 93% confidence
• Finding: requests.post(url, headers=headers, json=

VirusTotal

66/66 vendors flagged this skill as clean.