The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools such as git, gh (GitHub CLI), and various package managers (npm, pip, cargo, etc.) to reproduce bugs, fetch CI logs, and verify fixes. These operations are consistent with the skill's purpose as a debugging assistant.
[DATA_EXPOSURE]: The provided script scripts/collect-diagnostics.sh gathers environment information including OS details, resource availability, and a whitelisted set of safe environment variables (e.g., NODE_ENV, CI). It also captures the current working directory and the local username. This data collection is localized and intended to assist in troubleshooting environment-specific issues.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data sources such as stack traces, application logs, and test outputs. It incorporates security best practices by explicitly instructing the agent to sanitize this data—stripping hostnames, IPs, and customer information—before performing any external web searches.

ia-debugging