web3forms-contact-forms-for-static-websites

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md) instructs the agent to connect to the Web3Forms service via the Membrane CLI and run actions that return "Submissions" and other form data (e.g., "Forms -> Submissions" and "membrane action run ... the result is in the output field"), which are user-generated/untrusted inputs that the agent is expected to read and can drive automations, so untrusted third-party content could indirectly inject instructions.