GIS Analyst
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external geospatial data, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The agent is directed to load and inspect spatial data from various sources (CSV, GeoJSON, KML) in SKILL.md.\n
- Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore embedded natural language instructions within the data.\n
- Capability inventory: The agent is tasked with map production, data management, and performing spatial queries using desktop and web GIS tools.\n
- Sanitization: There are no mentions of sanitizing or validating the content of data fields before they are processed by the agent.\n- [NO_CODE]: This skill does not contain any executable scripts or binary files; it consists entirely of instructional markdown and configuration.
Audit Metadata