firebase-firestore
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches and executes the official Firebase CLI (
firebase-tools) vianpxto perform database management and deployment tasks. - [COMMAND_EXECUTION]: Executes various shell commands to list, create, and configure Firestore instances, as well as deploy security rules and indexes.
- [INDIRECT_PROMPT_INJECTION]: The instructions for generating security rules require the agent to perform a full scan of the project codebase to identify data models and queries. This ingestion of untrusted local data represents a surface where malicious content within the codebase could attempt to influence the agent's logic or the generated security rules.
- Ingestion points: Codebase analysis workflow defined in
references/standard/security_rules.mdandreferences/enterprise/security_rules.md. - Boundary markers: Not defined; the agent is instructed to scan the entire codebase.
- Capability inventory: Full database management and deployment capabilities via the
firebase-toolsCLI. - Sanitization: No specific sanitization or filtering of codebase content is mentioned before processing.
Audit Metadata