otel-name-span

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to "fetch the latest naming guidance" from public web pages (e.g., https://opentelemetry.io/docs/specs/semconv/general/naming/ and https://opentelemetry.io/blog/2025/how-to-name-your-spans/) and to follow any fetched content that contradicts the skill, meaning arbitrary third-party webpage content is ingested and can change agent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill explicitly instructs the agent to "fetch the latest naming guidance" at runtime from https://opentelemetry.io/docs/specs/semconv/general/naming/, https://opentelemetry.io/docs/specs/semconv/general/trace/, and https://opentelemetry.io/blog/2025/how-to-name-your-spans/ and to follow any fetched content that contradicts the local rules, so those external pages directly control the agent's behavior.