ClawHub
Back to skill

Security audit

Developer Skills

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly developer guidance, but it includes broad instructions for persistent background services and remote file transfer without enough user control.

Review this skill before installing. It may be useful as Chinese developer guidance, but do not let it create persistent services, start long-running background jobs, install unpinned packages, or push files to remote hosts unless you explicitly approve the exact files, commands, destinations, restart policy, and cleanup steps.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Findings (4)

T06 · System Persistence

Error
Location
SKILL.md:381
Finding

Persistent Background Service and Automatic Restart Instructions

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:298
Finding

Unpinned Network Package Installation Bypasses Python Environment Protections

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:527
Finding

Unrestricted Encoded File Transfer to a Remote SSH Host

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:121
Finding

API Credential Included in a URL Query String

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown skill is written as a general-purpose developer skill, but its manifest description is entirely in Chinese and the document consistently instructs behavior in Chinese without any opt-in or note that the skill is region-specific. Under the language/locale policy, forcing a specific language for a broadly scoped skill is a natural-language policy violation unless user choice or clear justification is provided.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 347)May include surrounding context.

})

text

**规则：** 修改 `main.py` 或任何模板路由后，启动后端并用 curl 访问一次页面路由（如 `/`、`/fund/{code}`）验证模板渲染不报错。`HTTP 500` 且日志为 `TemplateResponse() takes ...` 或 `KeyError: request` 时，优先检查此签名。

#### 🔴 Pitfall: 数据采集脚本写入表结构与 models.py 不一致
当项目同时存在 `database/models.py` 的规范 Schema 和采集脚本中内嵌的旧版建表 SQL 时，两者会互相覆盖，导致 API 查询失败、外键约束错误或数据字段丢失。

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 360)May include surrounding context.

md
**正确做法：**
1. 删除旧数据库（先备份为 `.db.bak`），用 `models.py` 的 `Database` 重新初始化；
2. 删除采集脚本中的自定义 `CREATE TABLE` 逻辑，改为复用 `Database.connect()` + `Database.init_tables()`；
3. 把采集脚本中的插入 SQL 改为调用 `Database` 的 `upsert_fund_info()` / `upsert_nav()` / `upsert_score()` 或 `execute_many()`；
4. 小范围测试（如 `MAX_FUNDS=10`）后，用 `PRAGMA table_info(table)` 验证字段数量。

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 360)May include surrounding context.

md
**正确做法:**
1. 删除旧数据库(先备份为 `.db.bak`),用 `models.py` 的 `Database` 重新初始化;
2. 删除采集脚本中的自定义 `CREATE TABLE` 逻辑,改为复用 `Database.connect()` + `Database.init_tables()`;
3. 把采集脚本中的插入 SQL 改为调用 `Database` 的 `upsert_fund_info()` / `upsert_nav()` / `upsert_score()` 或 `execute_many()`;
4. 小范围测试(如 `MAX_FUNDS=10`)后,用 `PRAGMA table_info(table)` 验证字段数量。

Static analysis

No suspicious patterns detected.