app-observability

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can be ingested into the LLM context via AI Observability/OpenLIT when it captures and forwards LLM prompts/completions (user-authored text) as trace/span data that the agent later summarizes or reasons over; this is not authored by the operating user.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime fetch-and-execute dependencies (e.g., the CDN script tag https://unpkg.com/@grafana/faro-web-sdk@latest/dist/library/faro-web-sdk.iife.js which loads and executes remote JS in the browser, and the wget URL https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/latest/download/opentelemetry-javaagent.jar which is downloaded and run as a javaagent), so these URLs fetch remote code that is executed at runtime.