linear-create
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Safe] (SAFE): The skill documentation describes standard usage of the
linear-clitool. No suspicious behaviors such as obfuscation, persistence, or privilege escalation were detected.\n- [Indirect Prompt Injection] (SAFE): The skill includes a pattern where it reads content from a local file (desc.md) to populate an issue description. While this is an ingestion surface for external data, it is a standard and expected functionality for this CLI tool.\n - Ingestion points:
desc.md(viacatcommand inSKILL.md)\n - Boundary markers: Absent (standard CLI piping usage)\n
- Capability inventory:
linear-cliexecution for creating bugs and tasks\n - Sanitization: Absent (relies on user/agent providing valid text content)
Audit Metadata