linear-favorites

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill utilizes the Bash tool to execute linear-cli commands for listing, adding, and removing favorites. No suspicious or unauthorized command patterns were detected.
  • Indirect Prompt Injection (LOW): The skill processes data from Linear (issue IDs and project information) which is an untrusted external source. 1. Ingestion points: Data entering the agent context via the output of linear-cli fav list. 2. Boundary markers: None present in the command examples. 3. Capability inventory: Includes the ability to modify Linear favorites via add/remove commands. 4. Sanitization: No sanitization or validation of the CLI output is performed before it is handled by the agent.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:03 AM