skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements robust security practices throughout its logic and instructions.
  • [COMMAND_EXECUTION]: The skill executes commands via Bash and Node.js spawnSync. It includes an isPathSafe utility that sanitizes file paths and command arguments against dangerous characters to mitigate command injection risks.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates research and installation from external sources like GitHub and arXiv. These are well-known or trusted services. The instructions include a mandatory multi-point security scan for any external content before incorporation.
  • [DATA_EXFILTRATION]: No patterns of sensitive data exfiltration were detected. The skill interacts with the local environment and whitelisted external domains for research purposes.
  • [CREDENTIALS_UNSAFE]: Metadata placeholders for environment variables like GITHUB_TOKEN are used appropriately to indicate requirements for MCP servers without hardcoding actual secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 11:19 PM