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@latestto 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_IDin an environment variable rather than hardcoding it, which aligns with industry best practices for configuration management. - [COMMAND_EXECUTION]: The skill uses the
Bashtool 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.mdto gather project-specific context. This is evaluated as an indirect prompt injection surface: - Ingestion points: Local file access to
CLAUDE.mdvia theReadtool. - Boundary markers: Not specified for the file contents.
- Capability inventory: High-privilege CLI operations via
Bashtool andfirebase-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