The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a bash utility script, find-polluter.sh, which uses find and npm test to isolate tests causing environmental pollution. It also provides examples for running diagnostic commands such as env, security, and codesign to gather information about the execution environment and configuration during debugging.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze external data sources such as error messages, stack traces, and logs. While this creates a potential surface for indirect prompt injection if logs contain attacker-controlled content, it is a standard and necessary part of the intended debugging workflow. The skill does not currently specify explicit boundary markers or sanitization for this ingested data.

systematic-debugging