qgis-data-extract
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes a statement that user instructions take priority. This is a common instructional pattern to ensure the agent remains helpful to the user and does not indicate an attempt to bypass safety guidelines or override system behavior.
- [DATA_EXFILTRATION]: The skill references a connection to
https://mcp.terra-lab.ai/mcp. This domain belongs to the skill's author (terralabai) and is used for its stated purpose of providing map data tools. It does not represent an unauthorized data exfiltration risk. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for processing untrusted data as it retrieves map features and metadata from external sources.
- Ingestion points: The skill ingests data from the
extract_open_datatool, including feature counts, attributes, and licensing information. - Boundary markers: The instructions do not define specific delimiters for separating tool output from the rest of the prompt context.
- Capability inventory: The skill uses tools to extract data and convert coordinates based on tool responses.
- Sanitization: No specific sanitization logic for the retrieved external data is described, but the risk is minimized by the skill's focus on structured GIS attributes.
Audit Metadata