clawshire-doc-extract-engine
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to upload PDF documents to a remote API (api.clawshire.cn) for structured data extraction. This behavior is clearly documented and intended.
- [EXTERNAL_DOWNLOADS]: The Python client includes functionality to fetch PDF content from user-provided URLs before uploading them to the extraction engine.
- [COMMAND_EXECUTION]: The provided Python script manages all API interactions using standard library modules (urllib), avoiding external dependencies.
- [DATA_EXFILTRATION]: While the skill transmits local document data to a remote server, this is the explicit and documented purpose of the tool.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (PDFs), presenting a standard but low-risk surface for indirect prompt injection targeting the extraction engine.
Audit Metadata