dev-git-workflow

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 perform web searches and verify recommendations using external sources (e.g., "verify via web search using data/sources.json" in Quick Start and the "Trend Awareness Protocol" / "Fact-Checking" sections), so the agent will fetch and interpret untrusted public web content that can materially influence its recommendations.