firebase-basics

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx -y firebase-tools@latest to execute Firebase commands. This fetches the official management package from the npm registry. As this is a well-known official tool, the download is considered part of standard development operations.
  • [DATA_EXPOSURE]: The instructions explicitly advise storing the FIREBASE_PROJECT_ID in an environment variable rather than hardcoding it, which aligns with industry best practices for configuration management.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run Firebase operations such as authentication (login), project selection (use), and initialization (init). These are standard administrative tasks performed through the official CLI.
  • [PROMPT_INJECTION]: The skill instructs the agent to read CLAUDE.md to gather project-specific context. This is evaluated as an indirect prompt injection surface:
  • Ingestion points: Local file access to CLAUDE.md via the Read tool.
  • Boundary markers: Not specified for the file contents.
  • Capability inventory: High-privilege CLI operations via Bash tool and firebase-tools.
  • Sanitization: None identified for processed file content. This pattern is common in development agents for context retrieval and is considered safe given the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:53 PM
Security Audit — agent-trust-hub — firebase-basics