magic-etl-cli
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Domo API (dataflow definitions and execution logs) that is then processed by the agent. This creates a surface for indirect prompt injection if a dataflow's metadata or name were to contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: The agent retrieves external content via
community-domo-cli dataflows get-definitionandcommunity-domo-cli dataflows execution-getcommands described inSKILL.md. - Boundary markers: Absent. The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when the agent parses the JSON results from the CLI.
- Capability inventory: The agent has the ability to execute shell commands (via
community-domo-cli), read/write local files (using the--body-fileargument), and trigger dataflow executions. - Sanitization: Absent. There is no evidence of filtering or validation of the retrieved JSON definition before it is used for subsequent operations.
Audit Metadata