The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard command-line security utilities such as adb, apktool, jadx, and frida to perform analysis on mobile devices and application binaries.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted mobile application data including binaries and source code. * Ingestion points: Untrusted application files are processed using apktool, jadx, and strings (SKILL.md). * Boundary markers: There are no explicit markers or instructions to isolate the agent from potential commands embedded in the analyzed data. * Capability inventory: The skill has access to shell commands, filesystem writing, and network operations through curl and the AWS CLI (SKILL.md). * Sanitization: No content validation or sanitization is performed on data extracted from external applications.

mobile-pentest