launch-feedback-synthesizer

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text is ingested via the runtime “Reads” path: the skill pulls/accepts untrusted feedback exports such as launch-platform community threads, store reviews, feedback-board posts, and support-ticket text (from connectors like scripts/connectors/hn.py / appstore.py / gdelt.py or pasted exports), and then clusters representative verbatim quotes into the LLM context.