enrich-csv
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates a specialized Python script based on a template and executes it locally using python3 to perform the enrichment process.
- [EXTERNAL_DOWNLOADS]: It installs the 'httpx' Python package from the standard PyPI registry to handle API communication.
- [DATA_EXFILTRATION]: Transmits CSV row data to the vendor's API at api.zo.computer. This is documented as an expected behavior using vendor-owned infrastructure.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion point: CSV cell data is read into the 'row_description' variable. Boundary markers: No delimiters or markers are used to isolate untrusted data in the API prompt. Capability inventory: The skill can execute commands (via script generation), write to files (modifying CSVs), and access the network (API requests). Sanitization: No filtering or escaping is performed on the CSV content before interpolation. This could allow malicious data within a CSV row to manipulate the behavior of the sub-agent processing the request.
Audit Metadata