single-sheet-reading-and-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from external Excel files.
- Ingestion points: The
load_and_clean_datafunction inSKILL.md(Step 2) usespd.read_excelto read data from a file path provided to the agent. - Boundary markers: There are no explicit delimiters or system instructions defined to prevent the AI from interpreting instructions embedded within the Excel spreadsheet cells.
- Capability inventory: The skill has the capability to write files to the local environment via
plt.savefig(Step 5) anddf.to_parquet(Step 6). It also renders HTML in the agent's output viadisplay(HTML)(Step 6). - Sanitization: While the skill performs basic data cleaning (regex numerical extraction and whitespace stripping), it does not sanitize against potential malicious text instructions within the data rows.
Audit Metadata