skills/ondata/opensdmx/sdmx-explorer/Gen Agent Trust Hub

sdmx-explorer

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the installation of the opensdmx CLI tool via uv tool install and DuckDB through its official website. The opensdmx tool is a resource developed by the skill's author, and DuckDB is a widely recognized service.
  • [REMOTE_CODE_EXECUTION]: Documentation in the skill suggests installing DuckDB by piping a script from its official domain (https://install.duckdb.org) to the shell. While this is a sensitive execution pattern, it targets a well-known and established service.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with and processes data from multiple external SDMX providers, creating a potential surface for indirect prompt injection.
  • Ingestion points: Statistical data is fetched from providers like Eurostat, ISTAT, and the World Bank as described in SKILL.md and istat-flow.md.
  • Boundary markers: There are no explicit instructions for using delimiters or warnings to ignore instructions that might be embedded in the retrieved statistical datasets.
  • Capability inventory: The skill utilizes the opensdmx CLI for data operations, writes files (CSV, YAML, README) to the local filesystem, and recommends generating and running Python scripts for visualization.
  • Sanitization: The instructions do not specify any sanitization or validation logic for the external data being processed.
  • [DYNAMIC_EXECUTION]: The skill encourages the agent to generate and execute Python scripts using the plotnine library to create custom visualizations that go beyond the capabilities of the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 02:38 PM