# repository-poisoning
標記為「repository-poisoning」的 2 篇文章
程式碼代理操縱
操縱生成、執行與審查程式碼的 AI 代理的技術，包括透過程式碼上下文進行注入、儲存庫投毒、執行環境攻擊，以及程式碼審查操縱。
code-agentscode-generationcode-executionagentsrepository-poisoningide-attacks
Repository 投毒 for Code 模型s
Techniques for poisoning code repositories to influence code generation models, including training data poisoning through popular repositories, backdoor injection in open-source dependencies, and supply chain attacks targeting code model training pipelines.
repository-poisoningcode-modelssupply-chaintraining-databackdoorsopen-source