firebase-basics
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the Firebase CLI (
firebase-tools) and management utilities (skills) vianpxfrom the npm registry. It also installs extensions directly from thefirebaseGitHub organization. These sources are categorized as trusted. - [COMMAND_EXECUTION]: Instructs the agent to perform environment setup, project creation, and authentication tasks using shell commands. This includes modifying system PATH variables and shell configuration files (e.g.,
~/.zshrc). - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: User-provided strings such as Firebase Project IDs, App IDs, and Display Names are ingested in
SKILL.mdand several setup guides. - Boundary markers: No explicit delimiters or boundary markers are used for the interpolated strings in commands.
- Capability inventory: The skill has extensive command execution capabilities via
npxand direct shell scripts across all files. - Sanitization: While
SKILL.mdprovides some descriptive constraints for Project IDs (e.g., 6-30 characters, lowercase), there is no technical sanitization or validation logic to prevent command injection if the agent receives malicious input.
Audit Metadata