neqsim-technical-document-reading
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements engineering data extraction logic using standard Python libraries such as pandas, pdfplumber, and python-docx. All processing occurs on local files provided to the agent.
- [COMMAND_EXECUTION]: The skill references a local developer tool,
devtools/pdf_to_figures.py, to convert PDF pages to images. This is a legitimate utility for processing engineering drawings and does not involve arbitrary command injection or unauthorized access. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse untrusted technical documents (PDFs, Excel, CSV, Images). While this creates an attack surface for indirect prompt injection, the provided extraction logic is primarily based on regular expressions and strict type casting (e.g., converting values to floats), which limits the execution of instructions embedded within the data. The documentation follows engineering best practices for data validation and quality scoring.
Audit Metadata