creating-ai-subscription
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for using official PostHog tools (
posthog:subscriptions-*) to manage a standard platform feature. All described behaviors align with the intended functionality of a reporting service. - [PROMPT_INJECTION]: The skill allows for a free-text
promptargument used by the backend to generate reports. No malicious override patterns, instructions to ignore safety guidelines, or bypass techniques were detected in the skill's instructions or examples. - [DATA_EXFILTRATION]: While the skill facilitates the delivery of project data to external targets (email and Slack), these are user-configured destinations. The process is governed by mandatory organization-level consent and requires the
query:readpermission scope, which prevents unauthorized data access.
Audit Metadata