pydanticai-docs

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs fetching the public URL https://ai.pydantic.dev/llms.txt ("Fetch Full Documentation"), so the agent is expected to retrieve and interpret external web content that could materially influence tool use or decisions.