smithery-homepage

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses a sensitive local configuration file at ~/Library/Application Support/smithery/settings.json to extract the user's Smithery API key and namespace, which are then written to a project-level .env file.
  • [INDIRECT_PROMPT_INJECTION]: The dashboard application is designed to ingest data from various external MCP tools (such as Linear issues, Gmail messages, and Notion pages). This creates a vulnerability surface where untrusted content from these external services could influence the agent's behavior during the development or execution of the homepage project.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs several software packages from the npm registry and utilizes the shadcn registry to scaffold the application UI with a remote template.
  • [COMMAND_EXECUTION]: The agent executes multiple shell commands to manage the project, including npx for initialization, npm for dependency installation, and smithery CLI commands to list and call MCP tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 12:18 AM
Security Audit — agent-trust-hub — smithery-homepage