mobile-security

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external mobile application packages (APK, IPA), which represents an inherent attack surface for indirect prompt injection if the analyzed files contain malicious instructions.
  • Ingestion points: Operations that read external binary data and resources, such as apktool, jadx, strings, grep, and sqlite3 (Reference: SKILL.md, reference/android.md, reference/ios.md).
  • Boundary markers: No explicit instruction-ignoring delimiters are provided for the agent when processing the output of these tools.
  • Capability inventory: The skill utilizes shell command execution (Bash) and file system operations (Read/Write) which could be targeted by successful injection.
  • Sanitization: The skill relies on the internal parsing logic of established security tools (e.g., jadx, apktool) without additional sanitization layers in the prompt instructions.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of standard mobile security utilities and references well-known open-source forensic tools.
  • Packages: Instructions to install frida-tools, objection, and biplist via standard package managers.
  • Tools: Provides links to established repositories and official sites for tools including jadx, apktool, Ghidra, and dex2jar for decompilation and analysis tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:42 AM