finding-experiments
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill's instructions guide the agent to resolve natural language references to experiment IDs using dedicated tools (
experiment-listandexperiment-get) within the PostHog ecosystem. There is no evidence of prompt injection, data exfiltration, or unauthorized command execution.
Audit Metadata