skills/kejidaren/open-design-codex/agent-browser/Snyk

agent-browser

Warn

Audited by Snyk on Sep 24, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (low risk: 0.10). The skill automates browser interaction with local preview URLs and web pages, which can expose the agent to outsider-authored free text when browsing external sites (low risk, as it requires active fetching/searching).

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 24, 2026, 05:59 AM

Issues

1