creating-experiments

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a procedural guide for experiment creation, using standard tool calls and parameters.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions remain within the functional scope of the PostHog vendor's expected operations.
  • [SAFE]: External references to other skills (e.g., configuring-experiment-rollout) follow a modular design pattern for agent capabilities and do not introduce unverifiable dependencies or remote code execution risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:19 PM
Security Audit — agent-trust-hub — creating-experiments