optise-helix-race-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill's mandatory workflow fetches and analyzes arbitrary user-supplied public URLs (see Section 4 Step 3 "Run fetch_page.py" and the included scripts/fetch_page.py), ingesting raw HTML and page content which the agent reads and uses to score and decide fixes—exposing it to untrusted third-party content that could carry indirect prompt injection.