wave-planner

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety guidelines or override agent behavior. The process is gated by two explicit user approval steps.
  • [DATA_EXFILTRATION]: The skill does not access sensitive credentials or system files, nor does it attempt to send data to external or unknown servers.
  • [EXTERNAL_DOWNLOADS]: No external script downloads or untrusted package installations are requested. References to model providers are standard for task routing.
  • [COMMAND_EXECUTION]: Orchestration is handled via the acpx session manager for controlled execution; no dangerous shell commands or privilege escalation attempts were found.
  • [REMOTE_CODE_EXECUTION]: No patterns of remote script execution or dynamic code loading from untrusted sources are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:53 AM