The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation and setup instructions specify the installation of the datacommons-client Python package, which is the official library for accessing Google Data Commons data. It also references pandas for data manipulation. These are standard packages from established registries.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest statistical and demographic data from the Data Commons API into the agent's context. This represents a potential indirect prompt injection surface common to all data-retrieval skills.
Ingestion points: Data is retrieved from the api.datacommons.org endpoint through the DataCommonsClient methods or the scripts/query_datacommons.py helper script.
Boundary markers: The instructions do not define specific delimiters for separating external data from agent instructions, though the use of Pandas DataFrames provides a structured format.
Capability inventory: The skill allows network access to the Data Commons API and the execution of Python scripts for data analysis.
Sanitization: The skill uses standard JSON parsing and Pandas conversion, but does not explicitly filter the content of the statistical observations for potential prompt injection patterns.

alterlab-datacommons