kelly-app-creator

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and does not include any executable scripts, commands, or remote code patterns, which mitigates risks of command injection or remote code execution.
  • [SAFE]: It contains explicit safety prohibitions against requesting or hardcoding sensitive credentials such as API keys and secrets.
  • [SAFE]: The skill mandates the use of dedicated external dependencies ($busabase and $busabase-app-creator) for all infrastructure and connection-related tasks, ensuring separation of concerns.
  • [SAFE]: The defined workflows (Research, Plan, Action, Retrospective) emphasize human oversight, including explicit opt-out windows and review points for all agent-generated actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 02:40 AM
Security Audit — agent-trust-hub — kelly-app-creator