level-up

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly calls fetch_langwatch_docs for the LangWatch prompt CLI (https://langwatch.ai/docs/prompt-management/cli.md) and relies on langwatch.prompts.get / the LangWatch service (https://app.langwatch.ai) at runtime to supply prompts that directly control the agent's instructions, making it a required external dependency.