onemap-gov-sg
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a remote Model Context Protocol (MCP) server hosted at
unbrowse.ai. This domain belongs to the skill's author and serves as the backend for the provided tools. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process data from
onemap.gov.sg, which represents an external data ingestion surface. - Ingestion points: Data is ingested via the
onemap_gov_sg__get_ss_searchtool and variousunbrowsescraping and task tools as defined inSKILL.md. - Boundary markers: There are no specific boundary markers or delimiters defined in the instructions to isolate external data from the agent's command context.
- Capability inventory: The skill is focused on data retrieval and does not include capabilities for local file system modification, shell command execution, or other high-privilege operations.
- Sanitization: The instructions do not specify any sanitization or validation logic for the content retrieved from the external website.
Audit Metadata