The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the openrndt package from PyPI, which is a library developed by the skill author, ondata.
[COMMAND_EXECUTION]: The skill makes extensive use of command-line tools such as openrndt, jq, curl, gdalinfo, and ogrinfo to interact with geographic services and process data. These operations are consistent with the skill's stated purpose of exploring territorial data.
[PROMPT_INJECTION]: The skill processes metadata and descriptions from the RNDT catalog and various OGC services (WMS/WFS). As this data is sourced externally, it presents an indirect prompt injection surface where malicious content embedded in the metadata could influence the agent's behavior.
Ingestion points: Data enters the context via openrndt search and openrndt get commands, as well as curl calls to OGC GetCapabilities endpoints.
Boundary markers: The instructions do not define explicit boundaries or warnings for the agent to ignore instructions embedded in the external metadata.
Capability inventory: The agent has access to shell execution, network requests via curl, and file manipulation via tools like ogr2ogr.
Sanitization: There is no mention of sanitizing or escaping the content retrieved from external geographic repositories.

rndt-explorer