design-review

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow uses a browser tool ($B goto, $B screenshot, $B snapshot, $B responsive) to navigate to a user-supplied/auto-detected target URL and extract rendered page content, which can include outsider-authored free text from arbitrary web pages into the agent’s LLM context (indirect prompt injection risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup step conditionally downloads and executes a remote installer script via curl -fsSL "https://bun.sh/install" and then runs it with bash, so https://bun.sh/install is fetched and executed at runtime.