scorable-otel-evaluation

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly tells the agent to look up framework-specific instrumentation in the public OpenInference catalog (https://github.com/Arize-ai/openinference) and to install/use the Scorable CLI from scorable.ai, so the agent will fetch and interpret public third‑party content that can change which instrumentation and commands it runs.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs executing remote installer code at runtime via "curl -sSL https://scorable.ai/cli/install.sh | sh", which downloads and executes code the skill requires (the Scorable CLI) and therefore is a direct remote code execution dependency.