安全决策报告
cogdx-health
Documentation-only skill that sends agent conversation history to an external third-party API without clear data handling policies or declared allowed-tools.
为什么得出这个结论
0/4 个维度触发 通过
声明与实际能力
声明资源与推断能力基本一致。
复核
隐藏执行与外联
提取到 1 个一般风险产物，需要结合上下文判断。
通过
攻击链与高危发现
没有形成明确的恶意路径。
复核
依赖与供应链卫生
没有完整依赖信息，供应链判断需要保留弹性。
风险分是怎么被拉高的
Missing allowed-tools declaration +15
SKILL.md has no allowed-tools mapping despite performing network requests
Undeclared data exfiltration +20
Sends full conversation history (prompts/responses) to external api.cerebratech.ai without clear data handling disclosures
Third-party data collection +10
Agent outputs containing user inputs routed to unknown third party with no privacy policy referenced
最关键的证据
中危 文档欺骗
Missing allowed-tools declaration
SKILL.md lacks allowed-tools metadata declaration. Despite this, the skill performs network requests to api.cerebratech.ai. The skill metadata should explicitly declare network:READ permission.
SKILL.md:1 Add 'allowed-tools: Bash' or appropriate tool declaration if this skill will be implemented with code.
中危 数据外泄
Conversation data sent to external third-party API
The skill sends 10-20 recent agent outputs (including user prompts and agent responses) to api.cerebratech.ai. This effectively exfiltrates conversation context to an external party without clear data retention, privacy, or consent policies documented.
SKILL.md:32 Document data handling practices, add privacy policy reference, and warn users that their prompts/responses will be sent to an external service.
低危 供应链
External service dependency on Cerebratech
The skill depends entirely on an external API (api.cerebratech.ai). If this service goes down, is compromised, or changes terms, the skill becomes non-functional. No fallback or local alternative exists.
SKILL.md:32 Consider documenting reliability expectations or offering a local analysis mode.
声明能力 vs 实际能力
网络访问 通过
声明 NONE
→ 推断 READ
SKILL.md:32 POST https://api.cerebratech.ai/cogdx-health 文件系统 通过
声明 NONE
→ 推断 NONE
N/A - no file operations 命令执行 通过
声明 NONE
→ 推断 NONE
N/A - no shell execution 环境变量 通过
声明 NONE
→ 推断 NONE
N/A - no env access 技能调用 通过
声明 NONE
→ 推断 NONE
N/A - no skill chaining 剪贴板 通过
声明 NONE
→ 推断 NONE
N/A - no clipboard access 浏览器 通过
声明 NONE
→ 推断 NONE
N/A - no browser usage 数据库 通过
声明 NONE
→ 推断 NONE
N/A - no DB access 可疑产物与外联
中危 外部 URL
https://api.cerebratech.ai/cogdx-health SKILL.md:25
依赖与供应链
没有结构化依赖告警。
文件构成
2 个文件 · 155 行
Markdown 2 个文件 · 155 行
需关注文件 · 1
SKILL.md Missing allowed-tools declaration · Conversation data sent to external third-party API · External service dependency on Cerebratech · https://api.cerebratech.ai/cogdx-health
其他文件 · api.md
安全亮点
No executable code present - skill is documentation only
API endpoint and data format are fully documented
No obfuscated code, base64 payloads, or suspicious patterns detected
No credential harvesting, SSH key access, or sensitive file operations
No reverse shell, C2, or direct IP-based malicious communication
Skill purpose is transparent (cognitive health assessment)
MIT license declared with author attribution