agentkind
SKILL.md文档中明确要求执行远程脚本 curl -fsSL https://agentkind.io/join.sh | sh,这是典型的供应链攻击向量,远程脚本内容完全不可控
SKILL.md 第18行要求执行 curl -fsSL https://agentkind.io/join.sh | sh,这是经典的供应链攻击向量。远程脚本内容完全不可控,可能在任何时候被篡改植入恶意代码。
SKILL.md:18 Why this conclusion was reached
2/4 dimensions flaggedDeclared resources and inferred behavior are broadly aligned.
1 high-risk artifacts or egress signals were extracted.
The report includes 3 attack-chain steps and 2 severe findings.
Dependency information is incomplete, so supply-chain confidence stays limited.
Attack Chain
Entry · SKILL.md:1
Escalation · SKILL.md:18
Impact · SKILL.md:18
What drove the risk score up
curl -fsSL https://agentkind.io/join.sh | sh 远程代码执行,脚本内容完全不可控
join.sh 脚本无版本锁定、无签名验证、无源码披露
密钥生成和存储逻辑隐藏在远程脚本中
依赖 agentkind.io 的 API 和脚本服务,无本地版本控制
Most important evidence
文档要求执行未验证的远程脚本
SKILL.md 第18行要求执行 curl -fsSL https://agentkind.io/join.sh | sh,这是经典的供应链攻击向量。远程脚本内容完全不可控,可能在任何时候被篡改植入恶意代码。
SKILL.md:18 API密钥生成逻辑隐藏在远程脚本中
密钥生成过程由远程 join.sh 脚本完成,凭证生成逻辑不透明。恶意脚本可在此环节植入后门或窃取生成的密钥。
SKILL.md:18 缺少 pip install 版本锁定
SKILL.md 未声明具体依赖版本,但元数据显示 requires.bins 包含 curl,表明可能需要安装 curl。
SKILL.md:14 文档格式不完整
SKILL.md 缺少 allowedTools、permissions 等标准声明字段,无法明确映射能力权限。
SKILL.md:1 Declared capability vs actual capability
SKILL.md:21-22 POST API 调用 SKILL.md:18 curl -fsSL https://agentkind.io/join.sh | sh SKILL.md:25 写入 .agentkind/credentials.json SKILL.md:15 需要 AGENTKIND_API_KEY Suspicious artifacts and egress
curl -fsSL https://agentkind.io/join.sh | sh SKILL.md:18
https://agentkind.io SKILL.md:4
https://agentkind.io/join.sh SKILL.md:18
https://agentkind.io/api/v1/agents/register SKILL.md:21
https://agentkind.io/api/v1/home SKILL.md:29
https://agentkind.io/skill.md. SKILL.md:39
https://agentkind.io/openapi.json. SKILL.md:39
Dependencies and supply chain
There are no structured dependency warnings.
File composition
SKILL.md