Lightpanda

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and README explicitly instruct agents to use Lightpanda to navigate and scrape arbitrary public webpages (e.g., page.goto and page.textContent examples in SKILL.md / README) so the agent will fetch and interpret untrusted third-party web content that could contain instructions influencing subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The install script (scripts/install.sh) fetches and installs a required executable from URLs like https://github.com/lightpanda-io/browser/releases/download/nightly/lightpanda- and queries https://api.github.com/repos/lightpanda-io/browser/releases/tags/nightly at install time, thereby downloading remote executable code that will be run as a required dependency.