gemini-paper-summary
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate academic research tasks as described. It reads local PDF files provided by the user and generates summaries using a well-known AI service.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the Google Gemini API (google-genai SDK). Downloads and network interactions are restricted to official Google services and standard package registries (PyPI for dependencies like pymupdf and google-genai).
- [CREDENTIALS_UNSAFE]: The skill follows security best practices for secret management by requiring the
GEMINI_API_KEYto be provided as an environment variable rather than hardcoding it or storing it insecurely. - [COMMAND_EXECUTION]: The provided Python script executes standard file I/O and network requests via the Gemini SDK. It does not use dangerous functions like
eval(),exec(), oros.system()to run arbitrary code from the processed PDF files.
Audit Metadata