The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions utilize platform-specific dynamic context injection (the exclamation-backtick syntax) to execute shell commands like cat on local configuration and protocol files during skill initialization. These commands are used to gather context from the workspace and do not incorporate external input.
[COMMAND_EXECUTION]: The agent is instructed to use Git-based commands such as git log, git diff, and git bisect for regression analysis. These commands are standard for a debugging utility and operate within the local project environment.
[PROMPT_INJECTION]: The skill is designed to analyze external, potentially untrusted data sources, which creates a surface for indirect prompt injection.
Ingestion points: The skill reads application logs, stack traces, and test outputs during the triage and investigation phases.
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions found within the logs or test data it processes.
Capability inventory: The skill has permissions to read and write files in the workspace and execute shell commands for testing and Git operations.
Sanitization: No validation or sanitization routines are specified for the log data or test results being analyzed.

debugger