firebase-hosting-basics

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The instructions establish an 'Iron Law' that mandates the use of Workload Identity Federation (WIF) and explicitly forbids storing long-lived service account JSON keys in environment files or CI/CD workflows, aligning with cloud security best practices.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx -y firebase-tools@latest to serve the production build locally. This fetches the official Firebase CLI tool from the public npm registry, which is a standard and expected operation for the skill's domain.
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by reading project configuration from files such as CLAUDE.md and various .env files to determine build paths and environment settings. This surface is inherent to the primary purpose of a deployment skill. Ingestion points: CLAUDE.md, .env files. Boundary markers: Absent. Capability inventory: Bash, Write, Edit, Glob. Sanitization: None specified for external file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:53 PM
Security Audit — agent-trust-hub — firebase-hosting-basics