feedback-synthesizer

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

• Third-party content exposure detected (high risk: 0.95). The skill’s required workflow explicitly includes aggregating qualitative feedback from outsider-authored channels (e.g., Intercom, App Store, Twitter, surveys) and then reading those free-form messages to extract quotes and themes, which would be ingested into the agent’s LLM context at runtime.