NYC

linear-dev-accelerator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill documentation instructs users to install and run the '@linear/mcp-server' package via npm and npx. While '@linear' is not on the predefined list of trusted organizations, the package is a standard and essential dependency for the skill's primary purpose of Linear integration. The severity is downgraded to LOW based on the primary purpose rule.
  • [PROMPT_INJECTION] (LOW): The skill exhibits a surface for Indirect Prompt Injection (Category 8) as it processes data from an external source (Linear).
  • Ingestion points: Data retrieved from Linear using tools like 'list_issues' and 'list_cycles'.
  • Boundary markers: The documentation does not specify boundary markers or instructions to ignore instructions embedded in the issue descriptions or comments.
  • Capability inventory: The skill includes tools to create and update issues, comments, and projects ('create_issue', 'update_issue', 'create_comment', 'create_project', 'update_project'), allowing an agent to modify state based on potentially injected instructions.
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from Linear before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:43 PM