graphics-api-hooking

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to fetch repository descriptions and archives from GitHub raw URLs based on user queries, which are outsider-authored source code repositories (low risk).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to dynamically fetch repository descriptions and code archives at runtime from the gmh5225/awesome-game-security GitHub repository to guide its behavior, which constitutes an unofficial operational dependency.