using-neon

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow fetches Neon documentation pages via curl from https://neon.com/docs/... (public web content), which is outsider-authored free text that can be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to run curl against https://neon.com/llms.txt and https://neon.com/docs/ at runtime to fetch documentation that would be injected into the agent context and thus directly control prompts/instructions.