juma-cro-audit
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and templates contain no malicious code, unauthorized network operations, or credential harvesting patterns. The functionality is limited to structured marketing analysis.- [PROMPT_INJECTION]: The skill analyzes untrusted external website content and analytics data, which represents an indirect prompt injection surface. 1. Ingestion points: live website walkthroughs and GA4 data (SKILL.md). 2. Boundary markers: absent. 3. Capability inventory: none (the skill only generates markdown text). 4. Sanitization: absent.
Audit Metadata