Paper Parse
PassAudited by ClawScan on May 1, 2026.
Overview
Paper Parse appears to be a coherent local PDF-to-Markdown and figure-extraction tool; the main thing to notice is that it runs a Python helper through uv with external PDF libraries.
Install if you are comfortable running a local Python PDF parser through uv. Use explicit PDF and output paths, and consider pinning or reviewing dependencies for high-assurance environments.
Findings (1)
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.
Running the skill may cause uv to use or install external Python PDF-processing packages before parsing the PDF.
The helper script declares external Python dependencies with version ranges for uv to resolve. These libraries are purpose-aligned for PDF parsing, but they introduce normal third-party package supply-chain exposure.
# dependencies = [ # "PyMuPDF>=1.23.0", # "pymupdf4llm>=0.0.10", # ]
Use it in a normal development environment, and review or pin dependency versions if you need stronger reproducibility or supply-chain control.
