linear-comments

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the linear-cli tool to manage issue comments on the Linear platform through shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that is not controlled by the user, creating a surface for indirect prompt injection.
  • Ingestion points: Issue comments are retrieved from Linear using the linear-cli cm list command.
  • Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data and instructions within the retrieved comments.
  • Capability inventory: The skill allows the agent to execute Bash commands and modify data via the linear-cli tool (creating, updating, and deleting comments).
  • Sanitization: No sanitization or validation logic is specified for the content fetched from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:13 AM
Security Audit — agent-trust-hub — linear-comments