adversarial-machine-learning

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and use content from the public GitHub raw URL https://raw.githubusercontent.com/gmh5225/awesome-ai-security/refs/heads/main/README.md, which is an open, untrusted third-party source whose contents the agent is expected to read and use to influence its actions.