ai-core

Warn

Audited by Snyk on May 14, 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 explicitly lets the client connect to arbitrary external URLs (e.g., fetchServerSentEvents/fetchHttpStream dynamic URL/options in ai-core/custom-backend-integration/SKILL.md) and the runtime consumes streamed AG-UI events (ag-ui-protocol/SKILL.md) including TOOL_CALL and message chunks (chat-experience/tool-calling SKILLs), meaning untrusted third‑party backends or public URLs can send content that the agent will parse and which can drive tool calls and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 14, 2026, 09:46 PM
Issues
1