irregular-excel-parsing
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Excel files, which represents a potential attack surface for indirect prompt injection. The impact is minimal as the skill is limited to data transformation.
- Ingestion points:
pd.read_excel()inSKILL.mdhandles external file data. - Boundary markers: None present in the instructions.
- Capability inventory: Restricted to pandas-based data manipulation; lacks network access, shell execution, or file writing capabilities.
- Sanitization: Includes basic header cleaning and type enforcement but does not filter for instructional content within cells.
Audit Metadata