The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill acts as a conduit for untrusted user data to be placed into GitHub issues.
Ingestion points: User-provided issue titles and descriptions (runtime).
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the user's issue content.
Capability inventory: Bash(gh issue:*) which allows creating and managing issues.
Sanitization: Absent; user input is passed to the CLI tool.
[Command Execution] (SAFE): The skill utilizes the gh CLI tool, but it is restricted to the gh issue namespace via the allowed-tools configuration, minimizing the risk of arbitrary command injection.
[Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, API keys, or access to sensitive file paths were detected. The skill relies on existing local authentication for the GitHub CLI.

github-issue-creator