mobile-android-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of Android application files (APK/AAB), which may contain adversarial content.
- Ingestion points: Decompiled source code, resource files, and system logs retrieved from target Android applications (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded within the target application's code or strings.
- Capability inventory: The agent uses tools including
adb,apktool,jadx,grep, andobjectionto extract and process data from the untrusted source. - Sanitization: No explicit sanitization or input validation is performed on the data extracted from the target application before it is processed by the agent.
Audit Metadata