linear-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to add an external MCP server endpoint (https://rube.app/mcp) to their client configuration. This server acts as the bridge for executing Linear operations via the Composio toolkit.
  • [COMMAND_EXECUTION]: The tool LINEAR_RUN_QUERY_OR_MUTATION allows the agent to execute arbitrary GraphQL queries against the Linear API. While this is a standard feature for advanced users, it provides a powerful capability for the agent to perform operations not restricted to the predefined tools.
  • [PROMPT_INJECTION]: The skill processes untrusted data from an external source (Linear issues, comments, and project descriptions), creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through tools like LINEAR_LIST_LINEAR_ISSUES, LINEAR_SEARCH_ISSUES, and LINEAR_GET_LINEAR_ISSUE (File: SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific warnings for the agent to disregard instructions potentially embedded within issue descriptions or comments.
  • Capability inventory: The skill has significant write and mutation capabilities, including creating/updating issues, project modification, and executing GraphQL mutations.
  • Sanitization: There is no documented validation or escaping process for retrieved data before it is presented to the agent's reasoning engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — linear-automation