firebase-storage
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill mentions the installation of the 'firebase_storage' package and references official documentation from Google. These sources are recognized as trusted and well-known services.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading file content and metadata from Firebase Cloud Storage, which could potentially serve as a vector for indirect prompt injection if the agent processes this data without boundaries.
- Ingestion points: File data is retrieved via
getData()and metadata viagetMetadata()inSKILL.md. - Boundary markers: Not present; the instructions do not specify delimiters for data retrieved from storage.
- Capability inventory: The skill includes capabilities for file upload, download, deletion, and metadata management.
- Sanitization: No sanitization logic is provided for external data retrieved from the storage bucket.
Audit Metadata