seo-maps
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external platforms, which serves as a potential vector for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from Google Maps, Bing Maps, Apple Maps, and OpenStreetMap, as well as business reviews from Google, Tripadvisor, and Trustpilot (documented in
SKILL.md). - Boundary markers: The instructions do not specify any boundary markers, delimiters, or explicit warnings for the agent to ignore instructions that might be embedded within the retrieved external content.
- Capability inventory: The skill possesses the capability to execute external tool calls (via the DataForSEO MCP) and perform file-write operations when generating the
MAPS-ANALYSIS-{domain}.mdoutput file. - Sanitization: No sanitization, validation, or escaping mechanisms are described for the external review text or business listing data before it is incorporated into the agent's context or final report.
Audit Metadata