lambrecht-creator-roi
Fail
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references multiple external blog posts from 'adspecialist.de' that are blacklisted by security scanners. These URLs are provided as sources for the agent to fetch and cite.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection. 1. Ingestion points: External creator audience data and store analytics. 2. Boundary markers: The skill uses review checklists and structured templates to guide the process. 3. Capability inventory: Fetches remote content and interprets external data. 4. Sanitization: Relies on manual checklist items for verification rather than programmatic sanitization.
Recommendations
- AI detected serious security threats
- Contains 4 malicious URL(s) - DO NOT USE
Audit Metadata