firebase-cloud-functions

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external companion skill firebase/agent-skills and directs users to a local document for installation and verification instructions. These resources are associated with the well-known Firebase service ecosystem.
  • [PROMPT_INJECTION]: The skill describes a surface for indirect prompt injection as it ingests user-provided inputs like schemas and use cases while maintaining command execution capabilities.
  • Ingestion points: Ingests "Use case", "Input schema", and "Auth/role requirements" as defined in SKILL.md.
  • Boundary markers: No specific delimiters or boundary markers for untrusted input are mentioned in the prompt instructions.
  • Capability inventory: Includes shell command execution through npm test, firebase emulators, and firebase deploy as shown in SKILL.md.
  • Sanitization: The skill provides explicit instructions to "Validate every input" and perform server-side validation for authentication and data in the resulting functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:30 PM
Security Audit — agent-trust-hub — firebase-cloud-functions