mastra

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime fetching of remote documentation such as https://mastra.ai/llms.txt (and other https://mastra.ai/*.md pages) via WebFetch to inject agent-friendly docs into the model context, so external content fetched at runtime can directly control prompts/instructions.