export-data-to-csv
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): The skill instructions do not contain attempts to bypass agent safety filters or override system constraints. Procedural language used ('MANDATORY', 'Do not proceed until') is workflow-oriented rather than malicious.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, API keys, or sensitive file paths were detected. The skill facilitates database exports requested by the user but does not contain logic to exfiltrate data to unauthorized destinations.- [Indirect Prompt Injection] (LOW): The skill possesses a surface for indirect prompt injection by interpolating untrusted user input into generated executable scripts.
- Ingestion points: Step 2 (Database type, table names, and column names provided by the user).
- Boundary markers: Absent; there are no instructions to the agent to treat this data as untrusted or to use delimiters.
- Capability inventory: The skill uses the 'Write' tool to create Robot Framework scripts (.robot) and documentation files (.md).
- Sanitization: Absent; no validation or escaping of the user-provided strings is mentioned before they are written to the test files.
Audit Metadata