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_KEY to 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(), or os.system() to run arbitrary code from the processed PDF files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 06:05 PM
Security Audit — agent-trust-hub — gemini-paper-summary