The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files such as CSV, Excel, and SQL databases, which creates a surface for indirect prompt injection. \n- Ingestion points: The scripts/pandas_profiler.py script and various documentation files utilize pandas functions to read external data. \n- Capability inventory: The skill enables extensive data manipulation and statistical analysis capabilities that could be exploited if an agent follows instructions embedded in malicious data files. \n- Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore potentially malicious content within processed data. \n- Sanitization: The skill does not implement or recommend sanitization or validation of data contents before analysis.

programming