ego-browser
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads outsider-authored free text via runtime browser inspection: agent scripts can navigate to search results (e.g., Google) and then ingest titles/snippets/contents from the results pages using
snapshotText()+click('@N'), or via helper tools that evaluate page DOM likesearchAndExtract(Google) and extract tweet text from the X timeline.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The macOS install script (scripts/install.sh) downloads and mounts a DMG from https://cdn.ego.app/channel/egobrowser_npx_referral/setup/macos/arm64/egolite.dmg and https://cdn.ego.app/channel/egobrowser_npx_referral/setup/macos/x64/egolite.dmg at runtime, which fetches and installs/executesthe remote ego lite app that the skill depends on.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata