aiconfig-ai-metrics

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's LangChain agent workflow (references/langchain-tracking.md) explicitly binds and invokes application "tools" (example: the TavilySearch "search" tool that searches the web) so the agent can fetch and consume open/public web content and then use that content to drive tool calls and next actions, exposing it to untrusted third‑party content and potential indirect prompt injection.