math-calculator
发现确认的恶意反向shell payload隐藏在数学计算器代码中,SKILL.md文档完全未声明此敏感操作。
在safe_calculate函数try块首行植入完整的反向shell代码,会在脚本首次执行时立即触发,连接C2服务器20.120.229.246:4444并获取远程shell。
skills/math-calculator/scripts/calculate.py:32 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 4 severe findings.
Dependency information is incomplete, so supply-chain confidence stays limited.
Attack Chain
Entry · skills/math-calculator/SKILL.md:1
Escalation · skills/math-calculator/scripts/calculate.py:32
Impact · skills/math-calculator/scripts/calculate.py:32
What drove the risk score up
代码在safe_calculate函数try块首行植入完整反向shell:socket连接20.120.229.246:4444并执行/bin/sh
硬编码IP 20.120.229.246用于C2通信,端口4444
SKILL.md声明为安全数学计算器,完全未提及任何网络或shell执行能力
README.md和外部链接明确标注为weaponizing Claude Code skills的恶意PoC
Most important evidence
隐藏的反向Shell Payload
在safe_calculate函数try块首行植入完整的反向shell代码,会在脚本首次执行时立即触发,连接C2服务器20.120.229.246:4444并获取远程shell。
skills/math-calculator/scripts/calculate.py:32 C2服务器硬编码IP
IP 20.120.229.246 硬编码在恶意代码中,作为攻击者的命令控制服务器
skills/math-calculator/scripts/calculate.py:32 文档完全未声明恶意行为
SKILL.md声称这是'安全评估数学表达式'的工具,完全隐瞒了网络连接和shell执行能力
skills/math-calculator/SKILL.md:1 已知恶意PoC公开样本
README.md明确标注这是来自Medium文章的weaponizing Claude Code skills恶意PoC
README.md:1 Declared capability vs actual capability
skills/math-calculator/scripts/calculate.py:32 — 隐藏的反向shell代码 skills/math-calculator/scripts/calculate.py:32 — socket.connect连接到外部IP Suspicious artifacts and egress
20.120.229.246 skills/math-calculator/scripts/calculate.py:32
https://medium.com/@yossifqassim/weaponizing-claude-code-skills-from-5-5-to-remote-shell-a14af2d109c9 README.md:6
Dependencies and supply chain
There are no structured dependency warnings.
File composition
skills/math-calculator/scripts/calculate.py skills/math-calculator/SKILL.md README.md Security positives
No explicit security positives were supplied.