service-area-seo
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data related to business profiles (addresses, service areas, and services) to provide SEO recommendations and interact with external tools. This ingestion of external data creates a potential surface for indirect prompt injection.
- Ingestion points: Business location and service data provided by the user in response to questions in
SKILL.md. - Boundary markers: The instructions lack explicit boundary markers or warnings to ignore instructions embedded within the business data.
- Capability inventory: The skill utilizes tool routing for geogrid visibility scans (Local Falcon) and keyword research.
- Sanitization: No explicit sanitization or validation of the user-provided business information is implemented.
Audit Metadata