seaborn
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill manages environment setup by installing
seaborn(version 0.13.2) along with optional statistical packagesscipyandstatsmodelsusing theuvpackage manager. These are well-known, established open-source libraries used extensively in the scientific computing community.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions for usingsns.load_dataset(), which retrieves example datasets from the library's official public repository. This is a standard and expected feature of the Seaborn library for demonstration and testing purposes.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data viapandas.read_csv()and Seaborn's dataset loading functions. This creates a surface for indirect prompt injection if the processed data contains malicious instructions. However, the skill provides specific operating procedures for the agent to validate inputs and verify results, and the data processing capability is necessary for the skill's primary function.
Audit Metadata