antithesis-agent-browser

Warn

Audited by Snyk on Jul 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill navigates to authenticated Antithesis pages and then extracts readable DOM text (including error banners/details and log event text) via agent-browser ... eval after runtime injection; those page contents are outsider-authored (by Antithesis and/or other users’ run/report data) and become LLM context through the extracted JSON returned to the agent.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 4, 2026, 11:01 PM
Issues
1
Security Audit — snyk — antithesis-agent-browser