openai-agents
Warn
Audited by Snyk on Sep 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill documents integration with remote Model Context Protocol (MCP) servers and connectors (such as
https://gitmcp.io/openai/codexandhttps://mcp.deepwiki.com/mcp), which ingest external text data at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata