extension-openai

Warn

Audited by Snyk on Aug 17, 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). Runtime path /chat(prompt : Text) (and OpenAI.runChatCompletion building ChatCompletionRequestUserMessage with content = #string(prompt)) ingests outsider-authored free text provided by callers directly from the canister API.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 17, 2026, 03:36 PM
Issues
1
Security Audit — snyk — extension-openai