linear

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to add an MCP server from Linear's official domain and execute a remote client via npx from a Linear-hosted endpoint.
  • [COMMAND_EXECUTION]: Setup steps require the execution of CLI commands like 'codex mcp' and 'npx' to configure the development environment and establish remote server connections.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes content from external Linear workspaces.
  • Ingestion points: Untrusted data is retrieved through tools such as 'get_issue', 'get_document', and 'search_documentation'.
  • Boundary markers: There are no instructions to encapsulate or delimit retrieved workspace content to prevent it from being interpreted as instructions.
  • Capability inventory: The skill includes powerful write operations including 'create_issue', 'update_issue', and 'create_comment' that could be targeted by malicious data.
  • Sanitization: The workflow does not include steps for validating or sanitizing retrieved text before it is used by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:33 PM
Security Audit — agent-trust-hub — linear