MinerU PDF Extractor
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears to do what it claims—convert PDFs with MinerU—but it uploads selected documents to MinerU and uses an API token that should be handled carefully.
Install/use this only if you are comfortable sending chosen PDFs or public PDF URLs to MinerU. Store the API token securely, verify the upload and download URLs are from the expected MinerU flow, and run extraction in a dedicated folder.
Findings (4)
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.
Your MinerU API token will be used for extraction requests.
The script sends the configured MinerU token in API requests; this is expected for a MinerU integration, but it is a credential that can use the user's MinerU account/API quota.
-H "Authorization: Bearer ${MINERU_TOKEN}"Set the token through environment variables, avoid sharing logs or shell history that expose related URLs, and leave MINERU_BASE_URL at the official endpoint unless you trust the alternative.
PDF contents may be processed and stored temporarily by MinerU or its storage/CDN providers.
The selected local PDF is uploaded to a remote presigned URL for MinerU processing; this is core functionality but means document contents leave the local machine.
curl -X PUT "$UPLOAD_URL" --upload-file "$PDF_PATH"
Only process documents you are allowed to send to MinerU, and verify that upload/download URLs come from the expected MinerU workflow.
Running the download step creates local ZIP and extracted result files.
The script downloads a result ZIP and extracts it locally; this is expected for the skill, but it writes files into the user's workspace.
curl -L -o "$ZIP_FILENAME" "$ZIP_URL" ... unzip -q "$ZIP_FILENAME" -d "$EXTRACT_DIR"
Run the scripts from a dedicated working directory and review the extracted files before reusing or sharing them.
Installer or registry views may not warn you up front that a MinerU token and local command-line tools are needed.
The registry metadata omits prerequisites that SKILL.md and the scripts disclose, including MINERU_TOKEN and curl/unzip; this under-declares requirements but does not show hidden behavior.
Required binaries (all must exist): none ... Required env vars: none ... Primary credential: none
The publisher should update registry metadata to declare the API credential and required tools.
