The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external geospatial data (vector and raster files), creating a surface for indirect prompt injection where malicious instructions could be embedded in data files.
Ingestion points: SKILL.md contains Python functions using gpd.read_file and rasterio.open to process external files.
Boundary markers: No delimiters or instructions to ignore embedded content are provided.
Capability inventory: The skill includes file system write capabilities via fig.savefig in the publication_map function.
Sanitization: No sanitization or content validation for incoming geospatial data is implemented in the provided scripts.

geospatial-analysis