catboost
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data via
pandas.DataFrameandcatboost.Poolas demonstrated in the code snippets inSKILL.md. This creates a vulnerability surface where malicious instructions could be embedded within categorical values or column names. The skill provides the capability to write files to the local file system usingmodel.save_model. No boundary markers, explicit data sanitization, or instructions to ignore embedded commands are present in the documentation.
Audit Metadata