The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/check_discoverability.py invokes the gh (GitHub) CLI to fetch repository metadata. It uses subprocess.run with argument lists, which is the recommended secure way to execute external commands as it prevents shell injection vulnerabilities.
[PROMPT_INJECTION]: The skill processes external data including repository descriptions, topics, and README.md content. While this represents an indirect prompt injection surface, the risk is mitigated by the skill's specific focus on metadata validation and the use of the gh CLI for controlled API interactions.

repo-discoverability