linear
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill documentation provides setup instructions involving a remote MCP server (mcp.linear.app). While this connects to an external service, it is the official infrastructure for the Linear platform and is essential for the skill's functionality.
- COMMAND_EXECUTION (LOW): Troubleshooting notes suggest using npx via WSL to run mcp-remote. This is a standard method for running MCP bridges and is provided as a configuration guide rather than a hidden execution payload.
- PROMPT_INJECTION (LOW): The skill is subject to indirect prompt injection (Category 8) as it processes user-generated content from Linear issues and comments. * Ingestion points: get_issue, list_comments, search_documentation (SKILL.md) * Boundary markers: Absent; the instructions do not specify delimiters for external content. * Capability inventory: create_issue, update_issue, create_comment, update_project (SKILL.md) * Sanitization: Absent; the agent relies on its base safety model when retrieving ticket data.
Audit Metadata