magic-etl
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes a workflow that involves reading data from external sources (Domo datasets), creating an attack surface where untrusted data could influence agent behavior.
- Ingestion points: The 'Workflow: Creating a New Magic ETL' section suggests querying input datasets using the
/api/query/v1/execute/<UUID>endpoint to retrieve schema and sample data. - Boundary markers: The provided code examples and instructions do not include the use of delimiters (like XML tags or triple quotes) or specific system instructions to ignore embedded commands within the retrieved dataset content.
- Capability inventory: The skill enables the agent to perform network operations via
curland manage production dataflows on the Domo platform, including creation, modification, and execution. - Sanitization: There is no mention of sanitizing, escaping, or validating the content of the external data before it is processed or used to build dataflow definitions.
Audit Metadata