firebase-ai-logic-basics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Firebase SDK (
firebase) and CLI tools (firebase-tools) via npm. These are provided by a trusted vendor and are standard for the described development environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill documents how to build applications that ingest untrusted user data (text prompts, images, audio, video) and process it using Gemini models. This creates a surface for indirect prompt injection attacks where malicious data could influence the agent's behavior.\n - Ingestion points: User input is ingested via
generateContent,generateText, and multimodal functions inreferences/usage_patterns_web.md,references/flutter_setup.md,references/usage_patterns_android.md, andreferences/ios_setup.md.\n - Boundary markers: Not explicitly implemented in the provided basic code examples.\n
- Capability inventory: The skill uses the
firebase_aiSDK to perform network requests to Firebase and Google AI backend services.\n - Sanitization: No specific input sanitization or escaping logic is shown in the tutorial snippets.
Audit Metadata