The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external Linear tickets and documents to determine its next steps.
Ingestion points: Data is ingested from Linear issue descriptions, gitBranchName fields, and project-specific documents via get_issue and get_document calls.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when the agent reads or summarizes these external descriptions.
Capability inventory: The skill possesses the capability to execute git commands (git branch), GitHub CLI commands (gh pr view), and perform write operations to the Linear API (update_issue, create_comment).
Sanitization: The skill lacks explicit sanitization or validation logic for the gitBranchName field or issue descriptions before they are used to influence shell commands or summary outputs.

kata-linear