xlsx-processing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process data from external Excel (.xlsx) and CSV files, creating a surface for indirect prompt injection.
- Ingestion points: The skill utilizes
pd.read_excel(),pd.read_csv(), andload_workbook()to ingest data from files that may originate from untrusted sources. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to differentiate between the agent's instructions and the data being processed from the files.
- Capability inventory: The skill includes file system write capabilities via
wb.save(),to_excel(), andto_csv(), allowing it to modify or create local files based on processed data. - Sanitization: There are no documented procedures for sanitizing, validating, or escaping the content read from cells before it is processed or potentially included in subsequent LLM prompts.
Audit Metadata