firebase-crashlytics

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the Firebase CLI using npx -y firebase-tools@latest and references SDKs from official Google Maven repositories and the official Firebase iOS SDK GitHub repository.
  • [COMMAND_EXECUTION]: Instructs the agent to execute Firebase CLI commands for managing projects and applications, as well as running an initialization script included in the iOS SDK during the build process.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where instructions are derived from project configuration files such as google-services.json, project.pbxproj, and Info.plist.
  • Ingestion points: Files are read in android_setup.md and ios_setup.md to extract App IDs and Bundle Identifiers.
  • Boundary markers: None present for the file content ingestion.
  • Capability inventory: The skill can execute shell commands via npx and modify application build files.
  • Sanitization: No specific sanitization logic is described for the data read from project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:04 AM
Security Audit — agent-trust-hub — firebase-crashlytics