The Agent Skills Directory

[SAFE]: The skill serves as a technical manual for using the legitimate security research framework, angr. It contains code snippets and best practices consistent with authorized security analysis and reverse engineering tasks.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install standard dependencies such as the angr framework via pip and system utilities like binutils and python3 via the apt package manager. These are well-known tools used widely in the technical community.
[COMMAND_EXECUTION]: The documentation provides instructions for running standard command-line tools like file to identify binary types and python3 to run analysis scripts. These commands are necessary for the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted binary files for symbolic execution.
Ingestion points: Target binaries and inputs processed by analysis scripts (e.g., target file in SKILL.md).
Boundary markers: The skill focuses on binary analysis via emulation; instructions are not interpreted as natural language by the tool.
Capability inventory: The skill uses file write operations to save solved flags (SKILL.md) and simulates network/file operations within the angr emulator.
Sanitization: The skill explicitly recommends running the output of its analysis (solved inputs) within a sandbox to mitigate risks from potentially malicious target binaries.

re-angr