dynamic-large-file-parquet-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes untrusted data from external Excel and Parquet files without specific security boundaries or delimiters.
- Ingestion points: Data is loaded from files via
pd.read_excelandpd.read_parquetinSKILL.md. - Boundary markers: No markers are present to isolate untrusted content or instruct the agent to ignore embedded instructions.
- Capability inventory: The skill is capable of local file writing (
to_excel) inSKILL.mdbut lacks network access or shell execution permissions. - Sanitization: No explicit validation or sanitization of the file content was observed before processing.
Audit Metadata