The Agent Skills Directory

[PROMPT_INJECTION]: The skill inherently processes untrusted external data, creating a surface for indirect prompt injection.
Ingestion points: The skill facilitates the ingestion of binary files, firmware images, and the resulting output from tools such as strings, rabin2, and gdb into the agent's context.
Boundary markers: No specific delimiters or safety instructions are provided to help the agent distinguish between its instructions and content extracted from target binaries.
Capability inventory: The skill utilizes powerful capabilities including full debugger access (gdb), instrumentation (Frida), and symbolic execution (angr), which allow for file system interaction and code execution.
Sanitization: There are no instructions for sanitizing or validating content retrieved from the analyzed binaries before it is interpreted by the agent.

reverse-engineering