kelly-digital-human

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or obfuscation were identified in the skill's instructions or scripts. The implementation serves the documented purpose of project management and solution design for digital humans.\n- [EXTERNAL_DOWNLOADS]: The skill uses version-pinned Node.js packages, including the hono framework and busabase-sdk, which are retrieved from the official NPM registry.\n- [COMMAND_EXECUTION]: Standard Node.js and pnpm commands are used for build processes and local development, as defined in package.json. These include bundling scripts with esbuild and running a local Hono server.\n- [DATA_EXFILTRATION]: The skill communicates with the Busabase platform (busabase.com) for persistent storage of QA decisions. This is an intended function of the skill. Authentication is handled via an OAuth flow, and credentials are saved locally in ~/.busabase with restrictive file permissions (mode 0600) to prevent unauthorized access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 10:36 AM
Security Audit — agent-trust-hub — kelly-digital-human