tilda
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a snippet that loads the Google Tag Manager script from
googletagmanager.com, which is an established and well-known service for website analytics. - [INDIRECT_PROMPT_INJECTION]: The skill provides a serverless function example (
handleTildaForminSKILL.md) that processes untrusted data from external form submissions, creating a potential attack surface. - Ingestion points: External form data is ingested via
req.formData()in thehandleTildaFormfunction. - Boundary markers: The implementation does not include specific delimiters or instructions to ignore potential commands embedded within the form fields.
- Capability inventory: The skill uses the
fetchAPI to perform network operations, sending data to a CRM and a Telegram bot. - Sanitization: The code does not perform explicit sanitization or filtering of the form data before interpolating it into the JSON payloads for external API calls.
Audit Metadata