formsmd-builder
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML boilerplate includes links to CSS and JavaScript bundles from
unpkg.com, which is a standard public CDN for web packages. - [COMMAND_EXECUTION]: The instructions guide the agent to perform API calls to
api.rebyte.aito manage form backends and retrieve submission data, which are vendor-owned resources. - [INDIRECT_PROMPT_INJECTION]: The skill creates a data ingestion path where untrusted user input from form submissions could influence agent behavior.
- Ingestion points: Data retrieved via the
resultsUrlAPI endpoint in JSON or CSV format. - Boundary markers: Absent; the instructions do not define delimiters to separate retrieved data from agent instructions.
- Capability inventory: The agent has the capability to perform network operations and generate executable HTML/JS content.
- Sanitization: Absent; the skill documentation does not provide procedures for validating or sanitizing the content of user-submitted form data.
Audit Metadata