webflow-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes data from external sources that are controlled by end-users (Webflow form submissions) or external actors (ecommerce order details).
- Ingestion points: Data is ingested via
webflow.forms.listSubmissionsandwebflow.orders.listwithin theSKILL.mdfile. - Boundary markers: Absent. The skill does not implement delimiters or specific instructions to the agent to disregard embedded commands in the retrieved data.
- Capability inventory: The skill environment allows for
Bash,Write,Edit, andReadoperations, which could be exploited if the agent obeys instructions hidden in the ingested data. - Sanitization: Absent. The logic does not validate or sanitize the content of form fields or order metadata before presenting it to the agent.
Audit Metadata