surveymonkey

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

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md) instructs the agent to use Membrane actions like "list-responses", "get-response-details", and "get-responses-bulk" to retrieve SurveyMonkey survey responses (user-generated/untrusted third-party content) that the agent is expected to read and could materially influence its decisions or subsequent tool actions.