The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues using gh issue view. There is a risk that malicious instructions could be embedded in issue comments or labels. The skill attempts to mitigate this by instructing the agent to specifically inspect the labels and the state of the working branch rather than blindly following instructions within comments.
[COMMAND_EXECUTION]: The skill executes gh (GitHub CLI) commands to manage issue state. This interaction is performed with a well-known service and is restricted to the specific task of issue tracking and coordination.

implement