typeform
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves untrusted data from Typeform (form responses and survey titles) at endpoints such as
/typeform/forms/{formId}/responsesas defined inSKILL.md. The instructions lack boundary markers or explicit sanitization requirements to prevent this external data from being interpreted as instructions by the agent. Capabilities include network access and form management via scripts inSKILL.mdusingurllib.requestandrequests. - [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute Python code using shell heredocs (e.g.,
python <<'EOF') to perform connection management tasks and API requests as demonstrated in the examples withinSKILL.md.
Audit Metadata