using-neon

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly instructs the agent to fetch and read Neon’s public documentation via curl (https://neon.com/llms.txt and https://neon.com/docs/), i.e., open third-party web pages the agent is expected to interpret and use to drive Neon-related claims and actions, which could allow indirect prompt injection from those pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using curl at runtime to fetch external markdown docs from https://neon.com/llms.txt and https://neon.com/docs/, which would inject remote content into the agent's context and directly influence prompts/responses.