pbvex-functions

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents the PBVex framework and its development workflow.
  • [COMMAND_EXECUTION]: Instructs the user to install the pbvex CLI tool using npm install --global pbvex. This is standard for developer tools.
  • [COMMAND_EXECUTION]: Provides commands for code generation (pbvex codegen), type checking (pbvex typecheck), and searching codebase (rg).
  • [DATA_EXPOSURE]: Explicitly warns against hardcoding secrets such as SMTP credentials or environment variables and recommends using isolated component environment bindings.
  • [PROMPT_INJECTION]: The skill uses clear instructional language for technical documentation and does not contain any patterns attempting to override agent behavior.
  • [DATA_EXFILTRATION]: Documents ctx.http.send for external service interaction but mandates destination allowlisting and validation to prevent arbitrary data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:13 PM
Security Audit — agent-trust-hub — pbvex-functions