qdrant-advisor

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

• Third-party content exposure detected (high risk: 0.85). The required workflow instructs the agent to fetch public web content at runtime from https://skills.qdrant.tech/search?... and then load linked SKILL.md/documentation pages, which are outsider-authored free text that becomes LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill explicitly directs the agent at runtime to fetch live skill content from https://skills.qdrant.tech/search?query=, which will be loaded and used to control the agent's prompts and guidance.