linear-automation

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill enables the agent to fetch and process external data from Linear issues, projects, and comments, which could contain instructions targeting the agent.\n
  • Ingestion points: LINEAR_LIST_LINEAR_ISSUES, LINEAR_GET_LINEAR_ISSUE, LINEAR_SEARCH_ISSUES (SKILL.md).\n
  • Boundary markers: None identified in instructions to separate data from instructions.\n
  • Capability inventory: LINEAR_CREATE_LINEAR_ISSUE, LINEAR_UPDATE_ISSUE, LINEAR_RUN_QUERY_OR_MUTATION (SKILL.md).\n
  • Sanitization: No sanitization or filtering of external content is described.\n- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to configure an external, third-party MCP server at https://rube.app/mcp as the primary tool provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:46 PM
Security Audit — agent-trust-hub — linear-automation