@fxri/toolkit
专为多人 + AI 跨项目协作打造:任务管理与配套的规范沉淀、规则、技能分发为主,附带多语言 CHANGELOG 与文档站。
This report shows the evidence for @fxri/toolkit@1.17.0. 1 of 74 known versions is blocked or flagged. The newest version, 1.17.8, is allowed.
AI security review
scanned · by lpm-firewall-aiThe earlier block is supported: CLI startup automatically replaces conflicting agent skill entries, and the replacement path recursively deletes the existing entry. This is a reachable agent-control hijack under the package's skill-management purpose, so the appropriate intent class is dangerous_capability.