android-security-assessment
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data including APK/AAB files, native libraries, and remote service responses, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests data from APK/AAB files, native libraries, device state (via adb/frida), and remote services (via burp) as identified in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the data being analyzed as untrusted or to ignore embedded instructions.
- Capability inventory: The skill utilizes a suite of analysis tools including /mobsf, /jadx, /apktool, /adb, /frida, and /burp to inspect the target application and environment.
- Sanitization: No sanitization, filtering, or validation mechanisms for the ingested data are mentioned in the instructions.
Audit Metadata