react-doctor

Warn

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a markdown file containing agent instructions from https://www.react.doctor/prompts/react-doctor-agent.md using curl.\n- [REMOTE_CODE_EXECUTION]: The instructions specify that the agent should follow every step in the fetched react-doctor-agent.md file, which is described as the 'single source of truth' and updates the agent's behavior dynamically. It also fetches per-rule prompts from https://www.react.doctor/prompts/rules/<plugin>/<rule>.md.\n- [COMMAND_EXECUTION]: The skill makes heavy use of npx react-doctor@latest, which downloads and executes the latest version of the react-doctor package from the npm registry every time it is invoked. This occurs for scanning, triaging, and configuring rules.\n- [DATA_EXFILTRATION]: While no explicit exfiltration was detected, the use of curl with headers to an external domain to fetch instructions creates a surface where local context could potentially be included in future updates to the remote playbook.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 5, 2026, 08:48 AM
Security Audit — agent-trust-hub — react-doctor