The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Uses npx to execute tsx, which may fetch the package from the official NPM registry if it is not already present on the system. This is standard behavior for Node.js-based CLI tools.- [DATA_EXFILTRATION]: Communicates with the official Linear API (api.linear.app), a well-known project management service, using an API key provided by the user via an environment variable. This follows security best practices for credential management.- [COMMAND_EXECUTION]: Runs a local management script (scripts/linear.ts) via tsx, a common and expected method for executing TypeScript code in a development or agentic environment.- [PROMPT_INJECTION]: The skill ingests external data from Linear issues, such as titles and comments, which constitutes a potential injection surface.
Ingestion points: Fetches issue titles, descriptions, and comments in scripts/linear.ts via the listIssues, getIssue, and searchIssues functions.
Boundary markers: No specific boundary markers or instructions are provided to the agent to distinguish between system instructions and data from Linear.
Capability inventory: Includes functions to update issue priorities, states, and add comments.
Sanitization: The listIssues function constructs GraphQL filters using direct string interpolation for the state and assignee fields, which represents a potential surface for structural injection if the source data is manipulated.

linear