The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to clone the frida-ios-dump utility from a third-party GitHub repository (https://github.com/AloneMonkey/frida-ios-dump) to facilitate application decryption.
[REMOTE_CODE_EXECUTION]: The workflow involves cloning an external repository and executing its main Python script (dump.py). This constitutes the execution of code downloaded at runtime from a source outside of the skill's own package.
[COMMAND_EXECUTION]: The skill makes extensive use of system shell commands for environment preparation and binary analysis, including unzip, otool, codesign, and various libimobiledevice utilities.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external Mach-O binaries and their metadata through tools like class-dump, creating a surface for indirect prompt injection.
Ingestion points: Output from commands like class-dump, otool, and strings are read into the agent's context to facilitate analysis.
Boundary markers: The skill does not include instructions for using delimiters or boundary markers when processing the output of these analysis tools.
Capability inventory: The skill has access to command execution, filesystem writes (e.g., headers output), and network utilities (ssh, iproxy).
Sanitization: The instructions do not specify any sanitization or validation of the data extracted from the external binaries before it is processed by the agent.

re-ios