kotlin-ui-adaptive-resources
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected in the skill instructions or metadata. The skill is purely instructional and follows safe practices for AI agent extensions.
- [EXTERNAL_DOWNLOADS]: The skill includes references to official Android and Kotlin development documentation. These resources are hosted on trusted domains (developer.android.com and kotlinlang.org) and are used to provide the agent with authoritative context for UI design.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project source code, creating a potential surface for indirect prompt injection. 1. Ingestion points: The agent uses
Read,Grep, andGlobtools to ingest local project files. 2. Boundary markers: None are explicitly defined in the skill instructions. 3. Capability inventory: The skill's allowed tools are limited to read-only operations; it has no network, file-write, or shell execution capabilities. 4. Sanitization: No specific sanitization or filtering logic is defined for the ingested content. The overall risk is evaluated as safe because the agent cannot perform any high-impact actions even if an injection occurs in the processed files.
Audit Metadata