yoetz
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow includes a “browser mode” path where the agent reads ChatGPT-side assistant text and UI-derived content from the user’s live Chrome session via CDP/extension transport, which is outsider-authored free text (ChatGPT responses) injected into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata