mvp-geo-optimizer
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user content to generate structured data and HTML.
- Ingestion points: Untrusted content enters via user-provided landing page text (SKILL.md).
- Boundary markers: Explicit delimiters for user input are not required by the instructions.
- Capability inventory: The skill focuses on content generation and does not define tools for shell execution or network access.
- Sanitization: No specific input sanitization steps are defined for data interpolated into schema templates (references/schema-templates.md).
Audit Metadata