The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill facilitates the installation of the goodissues CLI by downloading and executing shell and PowerShell scripts directly from the author's GitHub repository. While this is a standard installation method for the service, piped execution (curl | sh) is an execution vector that avoids local content verification.
Evidence: curl -fsSL https://raw.githubusercontent.com/agoodway/goodissues_cli/main/install.sh | sh in SKILL.md.
Evidence: irm https://raw.githubusercontent.com/agoodway/goodissues_cli/main/install.ps1 | iex in SKILL.md.
[COMMAND_EXECUTION]: The skill uses the goodissues CLI to perform all project and issue management tasks, dispatching subcommands based on user input.
[EXTERNAL_DOWNLOADS]: The skill downloads binary installation scripts and configurations from GitHub and communicates with the goodissues.dev API infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it accepts user-provided text for project names and issue descriptions and interpolates them into shell commands.
Ingestion points: User-provided values for --name, --description, and --title parameters in SKILL.md.
Boundary markers: The instructions tell the agent to wrap user-provided names in quotes, but do not provide comprehensive sanitization rules for all shell-sensitive characters (e.g., backticks, command substitution).
Capability inventory: The skill has the ability to write to the file system (via configure) and execute CLI tools.
Sanitization: No explicit sanitization or validation logic is defined for the interpolated user input.

goodissues