data_analysis
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (CSV, JSON, Parquet) which are untrusted ingestion points. Malicious content within these files could attempt to influence the agent's behavior during analysis or summarization.
- Ingestion points: Data is loaded from user-specified file paths in
scripts/explore_data.pyandscripts/summary_stats.py. - Boundary markers: No explicit delimiters or instructions are provided to separate data content from the agent's instruction context.
- Capability inventory: The skill allows reading and writing to the local filesystem via Polars and standard Python file operations.
- Sanitization: The provided scripts do not include logic to sanitize or escape data content before it is processed or presented to the agent.
Audit Metadata