talk-normal-llm-prompt

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

• Third-party content exposure detected (high risk: 1.00). This skill's instructions explicitly tell users to clone/pull the public GitHub repo (https://github.com/hexiecs/talk-normal.git) and copy the repo's prompt.md into the model's system prompt, meaning arbitrary third‑party repository content would be ingested as system instructions.