fivem

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly includes a "GitHub script search" step that instructs the agent to search public GitHub for candidate resources and present/top‑pick them, meaning the agent will fetch and act on untrusted, user‑generated third‑party content from the open web (GitHub).