webhook-transforms

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests external webhook payloads (e.g., SMS bodies, meeting transcripts, and social mentions such as "platform: 'twitter'") per the "On event received" phase and "Example Transforms" in SKILL.md, and those user-generated third-party contents are parsed and transformed into brain pages that drive entity extraction, task updates, and downstream actions—allowing untrusted text to materially influence agent behavior.