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 ... evalafter 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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata