hexabot-ai/action-creator

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a comprehensive developer guide for authoring Hexabot v3 actions, focusing on creating secure and reliable integrations.
  • [SAFE]: Implements a secure credential handling pattern in the provided examples (examples/create-crm-ticket.action.example.ts) by resolving secrets through a dedicated service (context.services.credentials.findOneValue) using credential IDs, rather than passing raw secrets through workflow data or inputs.
  • [SAFE]: Mandates the use of Zod schemas for input, output, and settings validation, which helps prevent malformed data processing and reduces the surface area for injection attacks.
  • [SAFE]: Provides a specialized 'Settings and Secrets Guide' that explicitly instructs against logging or returning raw credentials and emphasizes the use of idempotency keys for write operations.
  • [SAFE]: The security review checklist included in the skill covers critical topics such as PII redaction, SSRF prevention, and bounding LLM prompt context, demonstrating a high level of security maturity.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 12:58 PM
Security Audit — agent-trust-hub — hexabot-ai/action-creator