The Agent Skills Directory

[COMMAND_EXECUTION]: The run.py script executes a user-specified runner binary and an ELF file using the subprocess.Popen function. This capability is the core functionality of the skill, used to automate the execution and testing of the game port.
[INDIRECT_PROMPT_INJECTION]: The triage.py script parses log files generated during game execution. These logs are external data sources that could be influenced by the software under test, creating a potential surface for indirect prompt injection if the logs contain adversarial text.
Ingestion points: The triage.py script reads log files from the console/runs/ directory (e.g., latest.log).
Boundary markers: The script output does not include explicit instruction-boundary delimiters to signal the agent to ignore instructions embedded in the logs.
Capability inventory: The skill can execute local binaries (run.py), read/write project files, and perform incremental builds using cmake.
Sanitization: The script performs minimal sanitization by escaping markdown pipe characters for table formatting, but it does not filter for potential prompt injection patterns within the log content.

console-tester