instantly-core-workflow-b

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 ("Process") explicitly instructs the agent to "retrieve recent reply events and classify each response" from Instantly (user email replies) and to import lead CSVs, meaning it ingests untrusted, user-generated third-party content that can influence follow-up actions and routing.