The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard system utilities (uname, basename) and development tools (node, gh) to gather environment metadata and interact with GitHub. These operations are restricted to the skill's primary purpose of feedback reporting.
[DATA_EXFILTRATION]: The skill transmits system information (OS type, project name, and software versions) to the author's GitHub repository. This behavior is documented and includes a privacy toggle (anonymous mode) that asks for user consent before including environment details.
[SAFE]: No malicious patterns, such as prompt injection, obfuscation, or unauthorized access to sensitive files, were detected. The skill follows security best practices by using temporary files for markdown handling and providing the user with a preview before final submission.

omcustom-feedback