gemini-video-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Data Exposure & Exfiltration (SAFE): The scripts
analyze.pyandmanage_files.pyaccess the local filesystem to read video files and transmit them togenerativelanguage.googleapis.com. This behavior is the primary intended purpose of the skill and is directed at a legitimate service provider. - Indirect Prompt Injection (SAFE): Although the skill processes untrusted video content that could contain adversarial instructions, this is a fundamental risk of multimodal LLM applications. The skill relies on the backend model's safety guardrails to mitigate these risks.
- Credential Handling (SAFE): The skill follows best practices by requiring the
GOOGLE_AI_API_KEYto be provided via environment variables, ensuring that no secrets are hardcoded in the skill's source files. - Dependency Analysis (SAFE): No external Python or Node.js packages are required or installed. The skill relies entirely on the Python standard library for its networking and file operations.
Audit Metadata