firestore-operations-manager

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions or scripts. The instructions focus on legitimate Firestore management tasks and follow documented best practices.
  • [EXTERNAL_DOWNLOADS]: The skill references standard Node.js packages (firebase-admin, @firebase/rules-unit-testing) from official registries, which is expected for Firestore development.
  • [COMMAND_EXECUTION]: Includes a setup script (scripts/setup-firestore.sh) that uses the gcloud CLI for project configuration, representing standard infrastructure-as-code patterns.
  • [SAFE]: (Indirect Prompt Injection surface) The skill processes data from Firestore documents which could potentially contain untrusted instructions. This is an inherent risk for database management tools.
  • Ingestion points: Reads from Firestore collections in migration examples.
  • Boundary markers: No explicit instructions to the agent to treat document data as untrusted or ignore embedded commands.
  • Capability inventory: The agent has Bash access, file system access, and Firestore write capabilities.
  • Sanitization: Document data is processed directly without sanitization or validation steps mentioned in the prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 12:41 PM