The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: Processes CSV files for coordinate plotting and vector/raster data (Shapefiles, GeoPackages) for spatial analysis as described in the use cases.
Boundary markers: The skill does not define specific boundary markers or instructions to the agent to ignore embedded instructions within processed data.
Capability inventory: The skill possesses significant capabilities including PyQGIS headless scripting automation and execution of the qgis_process CLI tool (SKILL.md).
Sanitization: There are no sanitization or validation protocols mentioned to filter malicious payloads that might be embedded in geospatial metadata or CSV content.
[COMMAND_EXECUTION]: The skill utilizes the qgis_process CLI for headless automation, which involves executing system-level commands to perform geospatial operations.
[DYNAMIC_EXECUTION]: The skill facilitates the execution of PyQGIS scripts for batch processing and application bootstrapping, which involves running dynamically generated or referenced Python code within the QGIS environment.

qgis