linear-claude-skill
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates strong security awareness by instructing the agent to use Varlock for API key management, ensuring that sensitive LINEAR_API_KEY values are masked and never printed to the terminal or exposed in the conversation history.
- [COMMAND_EXECUTION]: The skill relies on the official Linear CLI and the execution of local TypeScript/JavaScript scripts via npx tsx to perform management tasks, which is standard for this type of integration.
- [EXTERNAL_DOWNLOADS]: The skill connects to the official Linear MCP server at https://mcp.linear.app/sse, which is a well-known and trusted service endpoint for Linear integration.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from external sources. 1. Ingestion points: Retrieves issue titles, descriptions, and comments from the Linear API via scripts like query.ts. 2. Boundary markers: Not explicitly defined for external content processing. 3. Capability inventory: Executes CLI commands, manages project states, and writes to environment configuration files. 4. Sanitization: No specific filtering or escaping mechanisms are documented for the ingested data.
Audit Metadata