analyzing-android-malware-with-apktool
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external APK files and extracts strings that are subsequently presented to the agent. This creates a potential surface for indirect prompt injection if an attacker embeds malicious instructions within an APK's resources or DEX files.
- Ingestion points:
scripts/agent.pyextracts strings from user-provided APK files using theandroguardlibrary. - Boundary markers: Extracted data is structured in JSON format, though the string values themselves are unvalidated.
- Capability inventory: The script's operations are limited to read-only file analysis and local JSON output.
- Sanitization: No sanitization or filtering is applied to the strings extracted from the APK metadata.
- [EXTERNAL_DOWNLOADS]: The script relies on the
androguardlibrary for its core functionality. While this is an external dependency, it is a well-established and standard tool within the mobile security community.
Audit Metadata