linear-claude-skill

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions and command templates for executing the Linear CLI and local TypeScript scripts (e.g., linear-ops.ts, query.ts) to automate project management tasks.
  • [EXTERNAL_DOWNLOADS]: The skill connects to the official Linear MCP server via npx mcp-remote at the well-known and trusted domain mcp.linear.app.
  • [PROMPT_INJECTION]: The skill processes external data from Linear issues and projects, which presents a surface for indirect prompt injection. 1. Ingestion points: Linear API outputs and CLI query results. 2. Boundary markers: No explicit boundary markers or ignore-instructions are defined in the command templates. 3. Capability inventory: The skill has the ability to execute shell commands and TypeScript scripts. 4. Sanitization: No explicit sanitization of issue content is mentioned.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill includes proactive documentation on securing API keys using Varlock and preventing credential exposure in logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:51 AM