skill-injection-defense

【数据与研究】Audits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious instructions, unsafe scripts, suspicious metadata, credential exposure, exfiltration paths, persistence mechanisms, and supply-chain risk. Use before installing, importing, publishing, promoting, modifying, or trusting third-party or …

独立 GitHub 快照 · 自动分类 · 以原作者文档为准