outline-wiki-setup

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/configure_mcp.py interacts with the system by executing the claude CLI via Python's subprocess.run(). It passes user-defined configuration values, such as the endpoint URL and API key, as command-line arguments. The implementation uses list-based argument passing, which is a secure practice that prevents shell injection vulnerabilities.
  • [DATA_EXFILTRATION]: The configuration script performs an outbound network request to a user-provided URL (OUTLINE_MCP_ENDPOINT) to verify the connection. If the user provides an API key, this secret is sent in the request headers to the specified endpoint for verification. This behavior is documented and necessary for the skill's primary function of setting up a remote service.
  • [EXTERNAL_DOWNLOADS]: The skill initiates network requests to external servers (either Outline Wiki's official cloud or a user-specified self-hosted instance) to perform a JSON-RPC initialization handshake. This is used to confirm that the endpoint is valid and reachable before registering it with the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 06:06 PM
Security Audit — agent-trust-hub — outline-wiki-setup