pandas
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard documentation and code examples for using the pandas library. All code snippets are benign and focus on legitimate data analysis workflows, such as grouping, resampling, and method chaining. The instructions follow modern best practices, including the use of the PyArrow backend and avoiding deprecated methods.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to ingest data from CSV files, which is a common pattern that creates a surface for indirect prompt injection if the data source is untrusted. 1. Ingestion points: pd.read_csv examples in SKILL.md. 2. Boundary markers: Not present in the provided code examples. 3. Capability inventory: Pandas library functionality for file reading and data transformation. 4. Sanitization: No specific data sanitization or filtering logic is shown in the tutorial snippets.
Audit Metadata