Base
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes data from untrusted external sources (CSV files, spreadsheets, and external databases) which could contain malicious instructions.
- Ingestion points: The skill explicitly supports importing data from CSVs and spreadsheets and connecting to external databases.
- Boundary markers: No specific delimiters or "ignore instructions" markers are defined to isolate data being processed from the agent's control logic.
- Capability inventory: The skill possesses the capability to write to the file system (via
doc.storeToURL) and execute SQL queries on connected databases. - Sanitization: While the documentation recommends parameterized queries as a best practice, the provided Python/UNO examples do not include explicit input validation or sanitization routines.
Audit Metadata