mentionedon-visibility-review
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by utilizing OAuth for authentication and explicitly instructing the agent never to request user credentials in conversation.- [INDIRECT_PROMPT_INJECTION]: The skill processes external business data which represents a potential injection surface.
- Ingestion points: Data is ingested through
get_visibility_reportandget_website_fixesinSKILL.md. - Boundary markers: Instructions define logical constraints for data processing (e.g., "Compare only the returned complete baseline") to minimize hallucinations or misinterpretations.
- Capability inventory: The skill is limited to reading data from the specified MCP endpoint and does not possess capabilities for file writing, system command execution, or arbitrary network access.
- Sanitization: The instructions mandate strict adherence to the provided data and explicitly forbid manufacturing information when baseline fields are null.
Audit Metadata