chatgpt-web
Warn
Audited by Snyk on Jun 16, 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’s runtime path reads outsider-authored free text from the ChatGPT web UI response (i.e., text generated by the ChatGPT service/assistant, not authored by the operating user) into the agent’s LLM context when it “Read[s] the latest assistant response from the page.”
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata