linear-claude-skill
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Runs the
linearCLI and local TypeScript automation scripts vianpx tsxfor project and issue management tasks. - [EXTERNAL_DOWNLOADS]: Fetches and runs utilities via NPM and interacts with the official Linear SSE endpoint at
https://mcp.linear.app/sse. - [PROMPT_INJECTION]: The skill processes untrusted data from external sources (Linear issues and comments), which presents a surface for indirect prompt injection.
- Ingestion points: Linear issue titles, descriptions, and comments retrieved via CLI or MCP.
- Boundary markers: No explicit instructions for delimiters or escaping are provided in the skill documentation.
- Capability inventory: Subprocess execution (bash), script execution (npx), and network access (WebFetch).
- Sanitization: No evidence of automated content sanitization or instruction filtering for incoming data.
Audit Metadata