The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/pio_debugger.py script executes the PlatformIO command-line tool (pio debug) using subprocess.run. The command is constructed as a list of arguments, which is a secure practice that prevents shell injection attacks.
[COMMAND_EXECUTION]: The script dynamically generates GDB command files in the system's temporary directory to automate debugging sequences. These temporary files are properly deleted using pathlib.Path.unlink after the debugging session completes.
[PROMPT_INJECTION]: The skill processes output from external tools and parses project configuration files (platformio.ini). This constitutes an indirect prompt injection surface (Category 8) where malicious project files could attempt to influence the agent's behavior through the data it reads. However, the risk is minimized as the skill only performs local debugging operations and does not have access to sensitive credentials or network-based exfiltration tools.

debug-platformio