universal-pdf-vision-parser

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This appears to be a coherent PDF-to-Markdown vision parser, but it sends PDF page images to DashScope/Qwen and needs careful API-key and package handling.

Install only if you are comfortable sending the selected PDF pages to DashScope/Qwen for cloud processing. Use a protected API key, avoid putting secrets directly in command history when possible, and install the Python dependencies in an isolated environment with pinned versions if you need stronger reproducibility.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Private or sensitive PDF contents may be processed by Alibaba Cloud DashScope/Qwen.

Why it was flagged

The script embeds rendered PDF page images as base64 data and sends them to DashScope's Qwen-VL-Max API. This is the intended operation, but it means document contents leave the local machine.

Skill content
{"image": f"data:image/png;base64,{base64_image}"}, ... MultiModalConversation.call(model='qwen-vl-max', messages=messages)
Recommendation

Only process documents that are allowed to be shared with that provider, and review the provider's privacy, retention, and compliance terms before use.

What this means

A DashScope key grants access to the user's provider account and may be exposed if pasted into shell history or visible process lists.

Why it was flagged

The skill uses a provider API key, which is expected for Qwen-VL-Max access. Users should still treat the key as sensitive, especially because SKILL.md demonstrates passing it on the command line and metadata does not declare a primary credential.

Skill content
parser.add_argument("--api-key", required=False, help="DashScope API Key")
Recommendation

Prefer using the DASHSCOPE_API_KEY environment variable or another secret manager, use a least-privilege key if available, and rotate the key if it may have been exposed.

What this means

Future dependency versions could change behavior or introduce vulnerabilities.

Why it was flagged

The setup instructions install unpinned Python packages from the package index. These dependencies are expected for PDF rendering and DashScope access, but versions and provenance are not fixed.

Skill content
pip install pymupdf dashscope
Recommendation

Install in a virtual environment and consider pinning reviewed versions of pymupdf and dashscope.