benchmark

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Phase 3: "Performance Data Collection") explicitly runs the browse daemon on arbitrary URLs ($B goto ) and uses $B eval to ingest page-generated performance/resource data from third-party webpages (user-supplied or auto-discovered), which the skill then uses to make benchmark comparisons and recommendations—so untrusted web content can materially influence decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's SETUP step downloads and executes a remote installer at runtime via curl -fsSL "https://bun.sh/install" -o "$tmpfile" and then runs bash "$tmpfile", so this external URL is fetched and executed as a required setup dependency.