The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) and git command-line tools to interact with repositories. These actions are restricted to viewing and closing issues, which is consistent with the skill's stated purpose.
[DATA_EXFILTRATION]: Accesses GitHub issue and Pull Request metadata (numbers, titles, bodies). All network activity is performed through the authenticated GitHub CLI, targeting only the repository configured by the user.
[INDIRECT_PROMPT_INJECTION]: The skill parses untrusted data from GitHub PR bodies and issue titles to identify issue numbers. The risk is mitigated by strict resolution logic (searching for specific patterns like 'Closes #N') and a required confirmation step before any destructive action (closing) is performed.
[PROMPT_INJECTION]: The instructions do not contain any attempts to override system prompts, bypass safety filters, or extract sensitive instructions.

closeissue