google-drive
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill documentation describes searching document contents via the
fullTextfield, which creates a surface for indirect prompt injection. \n - Ingestion points: The
fullTextfield indrive-queries.mdallows the agent to search and potentially process untrusted data from document contents and descriptions. \n - Boundary markers: No specific delimiters or safety instructions (e.g., "ignore embedded instructions") are defined for handling the results of these queries. \n
- Capability inventory: The referenced
scripts/google-drive.pyallows listing and filtering files based on their content. \n - Sanitization: The documentation does not specify any sanitization or validation of the retrieved content before it is processed by the agent.
Audit Metadata