MinerU PDF Extractor
Analysis
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.
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
curl -L -o "$ZIP_FILENAME" "$ZIP_URL" ... unzip -q "$ZIP_FILENAME" -d "$EXTRACT_DIR"
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.
Required binaries (all must exist): none ... Required env vars: none ... Primary credential: none
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.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
-H "Authorization: Bearer ${MINERU_TOKEN}"The script sends the configured MinerU token in API requests; this is expected for a MinerU integration, but it is a credential that can use the user's MinerU account/API quota.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
curl -X PUT "$UPLOAD_URL" --upload-file "$PDF_PATH"
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.