gemini
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external multimodal data including PDF, video, and audio files, which introduces an indirect prompt injection surface where malicious instructions could be embedded in the processed media.
- Ingestion points:
client.files.upload()methods used for contracts, presentations, and documentation files inSKILL.md. - Capability inventory: The skill utilizes the Google GenAI API to upload files and generate content based on those files.
- Boundary markers: The provided examples do not demonstrate the use of delimiters or specific instructions to ignore embedded commands in the source files.
- Sanitization: No sanitization or content filtering is implemented for the uploaded files prior to processing by the LLM.
Audit Metadata