brief-cultural-fit

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

• Third-party content exposure detected (high risk: 0.90). The skill's Procedure step 4 explicitly instructs the agent to read and cite "public signals" (engineering blog posts, podcast appearances, public Slack/Discord activity, careers‑page values, Glassdoor culture themes, public memos), so it will ingest untrusted, user‑generated open-web content that can materially influence its cultural‑fit judgments.