Skills
Navigate
skills/composiohq/awesome-claude-skills/NetSuite Automation/Gen Agent Trust Hub

NetSuite Automation

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes record data from NetSuite which could contain instructions intended to manipulate agent behavior.
  • Ingestion points: Records retrieved via NETSUITE_GET_CUSTOMER, NETSUITE_LIST_RECORDS, and NETSUITE_RUN_SUITEQL_QUERY are processed by the agent.
  • Boundary markers: There are no instructions providing delimiters or warnings to ignore embedded content within the NetSuite data.
  • Capability inventory: The skill includes high-impact write operations such as NETSUITE_CREATE_SALES_ORDER, NETSUITE_CREATE_CUSTOMER, and NETSUITE_UPDATE_CUSTOMER which could be abused if an injection is successful.
  • Sanitization: The instructions do not specify any filtering or sanitization of data retrieved from the ERP before it is processed by the agent.
  • [COMMAND_EXECUTION]: The NETSUITE_RUN_SUITEQL_QUERY tool allows for the execution of arbitrary SuiteQL SELECT statements against the NetSuite environment.
  • [EXTERNAL_DOWNLOADS]: The skill connects to the Rube MCP server at https://rube.app/mcp to facilitate NetSuite operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 02:15 AM