The Agent Skills Directory

[COMMAND_EXECUTION]: Uses the grep and git blame shell commands to search for specific strings and identify file line authorship. These commands are executed locally for the purpose of generating a report and do not involve remote network access or privileged operations.
[SAFE]: Processes data from source code comments which serves as an ingestion point for untrusted content. While this creates a potential surface for indirect prompt injection, the skill's functionality is restricted to reporting and does not provide an execution path for instructions embedded within those comments.

ponytail-debt