drizzle

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to "Fetch live documentation for up-to-date details" and provides the public URL https://orm.drizzle.team/llms.txt, so the agent will ingest external, third‑party web content that can materially influence its behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly states it will "Fetch live documentation for up-to-date details" and points to https://orm.drizzle.team/llms.txt, which is a runtime-fetched document that could inject remote instructions into the agent's context and thus directly control prompts.