clean-data-xls
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill attempts to install the
openpyxllibrary usingpipif it is not already present. While this is a common library for handling Excel files, dynamic installation of unversioned packages from public registries at runtime introduces a potential supply chain risk. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from active spreadsheets, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads data from active sheets or specified ranges (SKILL.md).
- Boundary markers: There are no instructions to the agent to treat cell content as untrusted or to ignore instructions embedded within the data.
- Capability inventory: The skill utilizes Python (
openpyxl) and Office JS to read and write data/formulas. - Sanitization: The instructions do not define sanitization or validation steps for the content being processed.
Audit Metadata