excel-reader
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's script automatically installs the
openpyxllibrary from the Python Package Index if it is not present. - [COMMAND_EXECUTION]: The
pipinstallation is performed usingsubprocess.check_callwith a list of arguments, which is a secure way to execute system commands without shell injection risks. - [PROMPT_INJECTION]: The skill ingests untrusted data from Excel files, which can contain malicious instructions intended to manipulate the agent. \n
- Ingestion points: Data ingestion occurs in
scripts/excel.pywhen loading workbooks. \n - Boundary markers: The skill does not use delimiters or provide warnings to the agent that the spreadsheet content is untrusted. \n
- Capability inventory: The skill's environment allows Python script execution and file system access. \n
- Sanitization: Cell data is formatted for display but is not sanitized to remove potential prompt injection sequences.
Audit Metadata