The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various command-line utilities for binary inspection, including file, strings, nm, and objdump to extract information from executables.
[DYNAMIC_EXECUTION]: Provides templates for Python-based exploit development using pwntools and symbolic execution frameworks like angr and Triton to analyze binary code paths.
[EXTERNAL_DOWNLOADS]: References well-known security research tools and their official GitHub repositories, such as cwe_checker, qira, and Triton for automated vulnerability detection and runtime analysis.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted binary files which serves as a potential attack surface.
Ingestion points: Binary files processed by analysis tools (SKILL.md, reference/protections.md).
Boundary markers: None present for input binaries.
Capability inventory: Shell command execution, file system access, and Python script execution (SKILL.md).
Sanitization: No explicit sanitization of binary strings or outputs before display is mentioned.

binary-analysis