The Agent Skills Directory

[SAFE]: The skill implements a standard workflow for task management within the Linear platform. It identifies work items based on status and dependencies, then updates those statuses to coordinate multi-agent or multi-session activities.
[COMMAND_EXECUTION]: The skill executes the /grill-with-docs internal command using an issue key retrieved from Linear, which is an expected behavior for this tool's automated workflow.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external data from Linear tasks: * Ingestion points: Linear task metadata and issue keys are retrieved from the Linear API during the task selection workflow (SKILL.md). * Boundary markers: The workflow in SKILL.md does not define specific delimiters or warnings to separate data retrieved from Linear from the agent's instruction context. * Capability inventory: The skill's capabilities are limited to status updates within the Linear tool and calling the /grill-with-docs command (SKILL.md); it does not have access to shell execution or local file writing. * Sanitization: The skill does not explicitly sanitize or validate the issue keys retrieved from Linear before using them as arguments in subsequent commands.

next-to-grill