seo-maps
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external business websites and third-party map data.
- Ingestion points: Business URLs and names provided as user arguments, and full HTML content retrieved from target websites via the
WebFetchtool. - Boundary markers: Absent. The instructions lack delimiters or warnings to prevent the agent from executing instructions potentially embedded in the fetched HTML or metadata.
- Capability inventory: The skill possesses network access via multiple APIs, web fetching capabilities, and file writing permissions (to create
.mdreports). - Sanitization: Absent. There is no evidence of filtering, escaping, or schema validation applied to the external data before it is processed or included in output.
- [PROMPT_INJECTION]: The skill includes instructions that force a specific temporal and technical context ("March 2026") using unverified or speculative information about AI capabilities to override the agent's baseline knowledge for SEO analysis.
- [EXTERNAL_DOWNLOADS]: The skill interacts with several external services to retrieve SEO and geographic data.
- Evidence: Fetches data from DataForSEO, Google Maps Platform, Geoapify, Nominatim, and Overpass API. These are well-known services consistent with the skill's declared purpose of local SEO mapping.
Audit Metadata