data-building-ledger
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to a remote MCP (Model Context Protocol) server at
https://archhub-mcp.fly.dev/mcp. This external endpoint is required for the skill to perform its primary function of retrieving building data without requiring local API keys. - [INDIRECT_PROMPT_INJECTION]: The skill ingests building ledger and permit information from external South Korean government APIs via the
archhubtools, representing a theoretical vulnerability surface common to data-fetching tools. - Ingestion points: Data returned from tools like
building_profile,building_floors, andbuilding_ledgermentioned inSKILL.md. - Boundary markers: The skill instructs the agent to use
[NOT_FOUND]to prevent hallucinations when data is missing, but it lacks specific delimiters (like XML tags) to isolate the external data from its own instructions. - Capability inventory: The skill utilizes a set of 11 informational query tools for data retrieval; it does not contain tools for system modification or file writing.
- Sanitization: The instructions do not define explicit sanitization or validation steps for the incoming API data.
Audit Metadata