abtesting-mobile

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references standard SDKs from well-known providers including Google Firebase and Optimizely. These are integrated using platform-standard package managers like CocoaPods, Gradle, and NPM.
  • [COMMAND_EXECUTION]: The skill provides instructions for using official CLI tools for Firebase, Optimizely, and Statsig to fetch and update remote configurations.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to fetch and process configuration data from external services, which could potentially contain malicious instructions if the source is compromised.
  • Ingestion points: Data is fetched from Firebase Remote Config, Optimizely, and Statsig APIs as described in SKILL.md.
  • Boundary markers: No specific delimiters or warnings are implemented in the provided usage patterns.
  • Capability inventory: The skill utilizes CLI commands and network API calls to manage remote configurations.
  • Sanitization: The instructions do not describe validation or sanitization of the fetched JSON parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:44 PM