firebase-ai-logic
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate documentation and code snippets for Firebase AI Logic, which is a verified product for mobile and web developers.\n- [EXTERNAL_DOWNLOADS]: Fetches the
firebaseSDK andfirebase-toolsCLI from the official NPM registry. These are well-known, trusted packages provided by the skill's authoring organization (Google/Firebase).\n- [COMMAND_EXECUTION]: Uses the Firebase CLI (firebase-tools) vianpxto perform project management tasks like listing apps and initializing services. These commands are standard for the described workflow and do not involve unauthorized privilege escalation or persistence.\n- [PROMPT_INJECTION]: Contains specific instructions for the agent regarding model selection (e.g., favoringgemini-flash-latestand avoidinggemini-1.5-flash). These instructions are operational constraints intended to ensure the agent uses the most appropriate model version and do not attempt to bypass safety filters or ignore prior instructions.
Audit Metadata