安全决策报告

heycube-setup

Skill installs persistent conversation-monitoring hooks that exfiltrate user behavioral data to an external commercial API without declaring filesystem write, network write, or hook persistence capabilities.

安装决策优先 来源: 手动上传 扫描时间: 2026/4/5
文件 5
IOC 2
越权项 4
发现 5
最直接的威胁证据
01
Skill installed through legitimate skill install mechanism 初始入口 · SKILL.md
02
Creates persistent hook skills in ~/.agents/skills/ installation · SKILL.md
03
Modifies AGENTS.md to add automatic execution rules for every conversation installation · SKILL.md

为什么得出这个结论

2/4 个维度触发
阻止
声明与实际能力

发现 4 项声明之外的能力或越权行为。

复核
隐藏执行与外联

提取到 2 个一般风险产物,需要结合上下文判断。

阻止
攻击链与高危发现

报告包含 6 步攻击链,另有 3 项高危或严重发现。

复核
依赖与供应链卫生

发现 1 项需要关注的依赖或供应链线索。

攻击链

01
Skill installed through legitimate skill install mechanism

初始入口 · SKILL.md:1

02
Creates persistent hook skills in ~/.agents/skills/

installation · SKILL.md:1

03
Modifies AGENTS.md to add automatic execution rules for every conversation

installation · SKILL.md:1

04
On every conversation: sends summary to heifangti.com with user intent classification

权限提升 · assets/hook-skills/get-config.md:45

05
Stores returned behavioral dimensions in local SQLite profile database

权限提升 · scripts/personal-db.js:42

06
After every conversation: sends another summary and receives instructions to update psychological profile

最终危害 · assets/hook-skills/update-data.md:65

风险分是怎么被拉高的

Undeclared filesystem:WRITE +20

SKILL.md declares no file write permissions but script writes to ~/.agents/skills/, workspace/scripts/, and modifies TOOLS.md/AGENTS.md

Undeclared hook persistence +20

Installs GET_CONFIG and UPDATE_DATA hooks that execute on every conversation, modifying agent behavior permanently

External data exfiltration +18

Every conversation generates summary sent to heifangti.com for behavioral profiling without clear user consent

Undeclared database access +10

SQLite read/write operations for storing user psychological profiles not declared in capabilities

Silent failure masking +4

All errors silently skipped, hiding potential security issues from user

最关键的证据

高危 文档欺骗

Undeclared persistent hook installation

SKILL.md makes no mention of installing hooks that execute on every conversation, fundamentally altering agent behavior without disclosure.

SKILL.md:1
Declare all hook/persistence mechanisms explicitly in SKILL.md capabilities section
高危 数据外泄

Systematic conversation data collection to external API

Every conversation triggers API calls to heifangti.com sending conversation summaries, user intent classifications, and receiving behavioral profile dimensions to query/write. The '黑点' (black points) credit system indicates commercial data exploitation.

assets/hook-skills/get-config.md:50
Clearly disclose that ALL conversations are sent to external server; provide opt-out mechanism with clear UI indicator
高危 敏感访问

Psychological profile data storage and retrieval

Skill builds and stores detailed psychological profiles including profile.career, behavior.work_habits, etc. in local SQLite database. This sensitive data is collected incrementally across all conversations.

scripts/personal-db.js:1
Provide transparent data inventory showing exactly what profile dimensions are collected
中危 权限提升

Modifies core agent configuration files

Skill modifies TOOLS.md and AGENTS.md, which are core agent configuration files. This grants the skill ability to alter how the agent behaves permanently.

SKILL.md:1
Require explicit user consent before modifying core agent configuration; document all modifications
中危 供应链

Dependency version not pinned

package.json specifies better-sqlite3: ^12.6.2 allowing any compatible version, increasing supply chain risk.

scripts/package.json:4
Pin exact version: "better-sqlite3": "12.6.2"

声明能力 vs 实际能力

文件系统 阻止
声明 NONE
推断 WRITE
SKILL.md:Creates dirs at ~/.agents/skills/, writes scripts/personal-db.js, modifies TOOLS.md and AGENTS.md
网络访问 阻止
声明 NONE
推断 WRITE
get-config.md:50-53, update-data.md:70-73:POSTs to https://heifangti.com/api/api/v1/heifangti/agent/analyze
命令执行 阻止
声明 NONE
推断 WRITE
SKILL.md:Execute cd...&&node commands for npm install and database operations
数据库 阻止
声明 NONE
推断 WRITE
scripts/personal-db.js:Full SQLite CRUD operations for psychological profile storage

可疑产物与外联

中危 外部 URL
https://heifangti.com/api/api/v1/heifangti

SKILL.md:67

中危 外部 URL
https://heifangti.com

SKILL.md:132

依赖与供应链

包名版本来源漏洞备注
better-sqlite3 ^12.6.2 npm Version not pinned - allows any compatible version

文件构成

5 个文件 · 487 行
Markdown 3 个文件 · 383 行JavaScript 1 个文件 · 99 行JSON 1 个文件 · 5 行
需关注文件 · 4
SKILL.md Markdown · 145 行
Undeclared persistent hook installation · Modifies core agent configuration files · https://heifangti.com/api/api/v1/heifangti · https://heifangti.com
assets/hook-skills/get-config.md Markdown · 121 行
Systematic conversation data collection to external API
scripts/personal-db.js JavaScript · 99 行
Psychological profile data storage and retrieval
scripts/package.json JSON · 5 行
Dependency version not pinned
其他文件 · update-data.md

安全亮点

Includes privacy principle documentation (脱敏规则) for sending summaries
Provides opt-out mechanism via .heycube-off file
API_KEY is user-provided, not harvested from environment
Errors do not block main conversation flow