prompting-claude-models

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch and quote live docs (e.g. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices), meaning external content is fetched during runs and can directly control prompts/instructions.