opentelemetry-validation

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow queries Observe datasets (Tracing/Span, Tracing/Span Event, Metrics/OpenTelemetry, log datasets, etc.) containing telemetry emitted by instrumented applications and infrastructure, which can include untrusted user-supplied request bodies, attributes, and messages.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external OpenTelemetry semantic convention schemas and file listings via curl from api.github.com and raw.githubusercontent.com at runtime, which constitute weak or uncontrolled external operational dependencies.