php-modernization
Warn
Audited by Snyk on Apr 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's ProviderAdapterRegistry (references/adapter-registry-pattern.md and SKILL.md) creates adapters from database Provider records (getEndpointUrl/apiKey) and the OpenAiAdapter.chat method performs HTTP requests to those external endpoints (used by LlmService->chat and ProviderController->testConnectionAction), so the agent will fetch and interpret arbitrary third-party responses configured via provider records that could contain instructions affecting its decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata