The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a shell script find-polluter.sh that automates the execution of npm test on files within the project. It also instructs the agent to run a local utility scripts/aegis-workspace.py. These are functional components of the debugging workflow.
[PROMPT_INJECTION]: The skill's workflow involves reading and processing external data such as error logs, stack traces, and git diffs. This represents an indirect prompt injection surface where maliciously crafted logs could attempt to influence the agent. The skill does not define specific sanitization or boundary markers for these ingestion points, although its structured investigation phases provide some inherent guardrails.

systematic-debugging