sheets-terminal-spreadsheet
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user and agent to install the 'sheets' tool from an external source using
go install github.com/maaslalani/sheets@mainand points to prebuilt binaries on GitHub Releases. - [REMOTE_CODE_EXECUTION]: The installation command
go install github.com/maaslalani/sheets@mainfetches and compiles remote code for execution on the local system. - [COMMAND_EXECUTION]: The skill is centered around executing shell commands to interact with the spreadsheet tool, including piping data from databases (
psql) and using programmatic cell modification commands likesheets budget.csv B7=10. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of CSV data from potentially untrusted external sources (files and stdin). Without defined sanitization or boundary markers, this data could contain malicious instructions designed to influence the agent's behavior during processing.
- Ingestion points: Reading CSV files (
sheets budget.csv) and stdin pipes (cat data.csv | sheets) as described inSKILL.md. - Boundary markers: None provided in the instructions.
- Capability inventory: The skill allows file read/write access and programmatic data modification.
- Sanitization: Not specified in the skill body.
Audit Metadata