agent-builder-tool

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of remote tool calls for managing the lifecycle of AI agents on the AgentPMT platform, including creation, updates, publishing, and archiving.
  • [SAFE]: All external resource references, including API endpoints and marketplace links, point to the vendor's own infrastructure (agentpmt.com), which is consistent with the provided author context.
  • [SAFE]: The skill implements security best practices by masking sensitive agent configuration fields such as system_prompt and chat_model in API responses to prevent accidental data exposure.
  • [SAFE]: No local command execution or unauthorized file system access patterns were detected. Installation instructions for companion skills target the official AgentPMT repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 03:38 AM