The Agent Skills Directory

[PROMPT_INJECTION]: The skill interpolates user-supplied input directly into shell commands, which presents an attack surface for indirect prompt injection.
Ingestion points: The <version> argument provided by the user in the command /upgrade-examples <version>.
Boundary markers: Absent. There are no explicit delimiters or instructions for the agent to validate the input structure.
Capability inventory: The skill has the capability to execute shell commands via git, find, sed, and gh.
Sanitization: Absent. The instructions do not specify sanitization or escaping of the version string before it is interpolated into shell commands.
[COMMAND_EXECUTION]: The skill relies on shell commands to perform its primary function of repository maintenance.
Documentation: Uses git for branch management and commits, find and sed for file modification, and gh for interacting with GitHub.
Context: The command execution is within the expected scope of a developer-oriented skill meant for codebase maintenance.

upgrade-examples