codex-supergraph
Warn
Audited by Snyk on Mar 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md and references/prediction-markets.md) explicitly directs the agent to query the public GraphQL endpoint https://graph.codex.io/graphql to fetch prediction event/market descriptions, questions, trades, and trader profiles (user-generated/open-web content) that the agent is expected to read and can materially influence subsequent queries or actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata