The Agent Skills Directory

[External Downloads] (SAFE): The skill references the official Linear MCP server URL (https://mcp.linear.app/mcp). This is the primary and intended communication channel for the skill and originates from a trusted service provider (Linear).
[Indirect Prompt Injection] (LOW): The skill processes data from Linear (issues, comments, and documents) which can contain untrusted content. A malicious user or external collaborator could embed instructions in a ticket to influence the agent's actions during triage or updates.
Ingestion points: list_issues, get_issue, get_document, and list_comments as defined in the available tools in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded content were found in the prompt templates.
Capability inventory: The skill has write capabilities including create_issue, update_issue, and create_comment.
Sanitization: No explicit sanitization or validation of the retrieved ticket data is performed before processing.

linear