The Agent Skills Directory

[DATA_EXFILTRATION]: The skill is designed to read local files and transmit their contents to a remote API endpoint at https://chartgen.ai/api/platform_api/.
Evidence: The documentation explicitly states that data files are base64-encoded and sent to the ChartGen API for analysis and visualization.
Scope: This includes sensitive file formats such as .xlsx, .xls, and .csv which often contain proprietary or personal information.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files using natural language instructions, creating a vulnerability surface for indirect injection.
Ingestion points: Data enters the agent context through the --file and --json parameters in the data_analysis.py, data_interpretation.py, and data_visualization.py scripts.
Boundary markers: There is no evidence of boundary markers or instructions to ignore embedded commands within the processed data files.
Capability inventory: The skill possesses the capability to read arbitrary local files provided via arguments and perform network requests to an external service.
Sanitization: No sanitization or validation of the input file content is mentioned before it is passed to the analysis engine.
[COMMAND_EXECUTION]: The skill relies on the execution of Python scripts that perform both file system access and network operations.
Evidence: The documentation instructs the user to run scripts like python scripts/data_analysis.py, which take local paths as input and interact with a remote API.

data-analysis