codex-pr-feedback-loop
Warn
Audited by Snyk on Jun 19, 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 runtime path is the thread automation polling the current GitHub PR via paginated GraphQL and ingesting review thread bodies/comments authored by other users (outsider PR reviewers) into the agent’s LLM context for classification and fixing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata