xlsx
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Excel workbooks and JSON specifications which could be used to influence agent behavior.
- Ingestion points: Data is ingested from external files in
scripts/inspect_xlsx.py,scripts/edit_xlsx.py, andscripts/create_xlsx.py. - Boundary markers: The skill does not implement specific delimiters or instructions to separate untrusted cell data from the agent's system prompts.
- Capability inventory: The skill can read from and write to the local filesystem using the openpyxl library.
- Sanitization: No sanitization or validation of cell content is performed to filter out potential instruction-like strings.
Audit Metadata