formcan

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows the agent uses Membrane to connect to the external FormCan API and run actions like "Get Submission" and "List Form Submissions" that retrieve user-generated form responses, PDFs, and attachments from the public service, which the agent is expected to read and which could materially influence subsequent actions.