brand-kit

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches and parses arbitrary public websites (Path 2: "Fetch the homepage" and related CSS/manifest/favicon) and reads page copy for voice extraction (Path 5: "Fetch the homepage hero + 1–2 deeper pages"), which are untrusted third‑party sources that the agent must interpret and that materially influence downstream behavior (voice rules used by other skills) as part of the required workflow.