linear
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Unverifiable Dependencies (MEDIUM): The
linearshell script automatically executesnpm installifnode_modulesis not present. This triggers the download and execution of packages from the npm registry at runtime without manual intervention. - Indirect Prompt Injection (LOW): The skill ingests untrusted data from the Linear platform (titles, descriptions, comments) which could contain malicious instructions designed to manipulate the agent. 1. Ingestion points: Commands
linear issue viewandlinear issue listfetch external content. 2. Boundary markers: None identified. 3. Capability inventory: The skill can create, update, and delete issues. 4. Sanitization: No sanitization or escaping of external content is documented or performed in the wrapper script.
Audit Metadata