The Agent Skills Directory

[SAFE]: The skill provides documentation and usage patterns for more than 50 IDA Pro modules, including ida_bytes, ida_funcs, ida_hexrays, and others. Each file was analyzed for the presence of malicious instructions or hidden payloads.
[NO_CODE]: The skill consists entirely of Markdown and reStructuredText documentation files intended to guide an AI agent in generating valid IDAPython scripts. There are no executable scripts (.py, .js, .sh) or binaries included that pose a risk to the host environment.
[DATA_EXPOSURE]: While the API documentation covers functions for reading memory and accessing the registry (e.g., ida_registry), these are presented in the context of standard reverse engineering workflows and IDA's internal configuration management. No instructions exist to target sensitive user files or exfiltrate data.
[REMOTE_CODE_EXECUTION]: Documentation for the ida_expr and ida_loader modules describes functions for compiling and executing IDC scripts. However, these are legitimate parts of the IDA Pro SDK, and the skill does not instruct the agent to download or execute untrusted code from the internet.
[OBFUSCATION]: A thorough scan for Base64 encoding, zero-width characters, homoglyphs, and hidden text patterns yielded no results. All content is transparent and readable.

idapython