android-development
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions to utilize a specific plugin ('Superpowers') and prioritize its methods. This is an environment-specific tool preference rather than a safety bypass. Additionally, the skill patterns establish a surface for indirect instructions through external API data (Retrofit) and user input (Compose). Ingestion points:
references/api-integration.mdandreferences/screen-patterns.md. Boundary markers: Absent. Capability inventory: Network access, file-system interaction, and command execution (Gradle). Sanitization: Structural DTO mapping is used to validate data schema. - [SAFE]: External references target official Google Android sample repositories and reputable libraries, posing no security risk.
Audit Metadata