The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon requirements from external, potentially untrusted sources.
Ingestion points: Task descriptions from Linear tickets, issues, user conversation history, and repository-level configuration files such as AGENTS.md.
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings to help the agent distinguish between data to be processed and instructions to be followed within external content.
Capability inventory: The skill possesses significant capabilities, including local file modification, Git branch management, committing code, and pushing changes to remote repositories.
Sanitization: There are no explicit instructions to sanitize, validate, or filter the content retrieved from tickets or repository files before the implementation phase.
[COMMAND_EXECUTION]: The skill utilizes standard Git commands to manage the development lifecycle.
Evidence: The instructions explicitly direct the agent to use git ls-remote, git fetch, git push, and git rev-parse to synchronize with remote repositories and manage branches. These operations are core to the skill's functionality and are used within the scope of the target repository.

complete-work