linear
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the
@useclawlink/clitool for authentication (login,connect) and for executing Linear operations (actions,describe,run). - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and execute the
@useclawlink/clipackage from the NPM registry to facilitate the integration. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Linear, such as issue descriptions, comments, and attachments, which serves as a potential ingestion point for malicious instructions intended to influence agent behavior.
- Ingestion points: Data retrieved through actions like
linear_get_attachmentand general issue reading operations described in the CLI usage. - Boundary markers: The skill provides a manual oversight instruction: "Reads first; confirm with the user before any write."
- Capability inventory: The agent is granted shell command execution capabilities and write access to the Linear API (creating issues, projects, and comments).
- Sanitization: There are no explicit sanitization or filtering protocols defined in the skill instructions for handling data returned from the Linear API.
Audit Metadata