Jotform Automation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions direct the user to include the Rube MCP server from
https://rube.app/mcp. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Jotform such as form names and activity history which could contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: External data is ingested through the
JOTFORM_GET_USER_FORMSandJOTFORM_GET_USER_HISTORYtools as specified inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific warnings to the agent to disregard instructions embedded within the Jotform data.
- Capability inventory: The skill provides comprehensive tools for inspecting Jotform forms, user account details, folders, and history.
- Sanitization: There is no evidence of sanitization or content filtering for the data retrieved from the Jotform API.
Audit Metadata