nutrient-document-authoring

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly points to "single-fetch LLM-curated dumps" (e.g. https://www.nutrient.io/api/document-authoring/llms.txt, https://www.nutrient.io/guides/document-authoring/llms.txt, https://www.nutrient.io/llms.txt), which are intended to be fetched at runtime and would directly supply/control prompts/instructions to an LLM.