early-access-designer
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data including waitlist exports, tester counts, and web analytics data. It correctly implements security best practices by instructing the agent to treat these records as untrusted input and explicitly warns never to follow instructions embedded within these data sources.
- [DATA_EXPOSURE]: The skill manages state by writing program designs and stage definitions to local
memory/directories. This behavior is restricted to the skill's own data scope and does not involve access to sensitive system configurations or user credentials. - [COMMAND_EXECUTION]: No shell command execution, subprocess spawning, or administrative privilege requests were found.
- [EXTERNAL_DOWNLOADS]: The skill references official App Store and Play Store documentation for platform constraints. These are well-known, trusted sources and do not involve executable code downloads.
Audit Metadata