T07 · Tool Hijacking and Spoofing
- Location
scripts/dameng_tool.py:226- Finding
Unverified Dynamic Import of a Mutable External Converter Module
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly a coherent developer/database assistant, but it includes under-scoped high-impact integrations that users should review before installing.
Install only if you are comfortable reviewing and controlling the external integrations. Avoid using the generic `run <skill>` feature with untrusted skills, do not place database passwords on the command line, use only approved HTTPS LLM endpoints, and treat any SQL/code/chat content submitted to the LLM as leaving your machine. Review or remove the external dm_converter dependency path before using SQL conversion or diagnostics.
scripts/dameng_tool.py:226Unverified Dynamic Import of a Mutable External Converter Module
scripts/changshu_assistant_main.py:110LLM Credentials and Prompt Data Can Be Transmitted over Plaintext HTTP
scripts/dameng_tool.py:1239Database Password Accepted as a Plaintext Command-Line Argument
scripts/dameng_tool.py:884Unvalidated Schema Identifier Is Interpolated into SQL
templates/QUICKSTART.md:18Installation Guidance Uses Unpinned Third-Party Dependencies
templates/QUICKSTART.md:190Privacy Documentation Incorrectly Claims That Data Is Never Uploaded
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Prompt template CRUD and rendering with persistence to local files are materially different from the stated database-migration/security-scan/search focus. Hidden local write behavior can surprise users, create persistence they did not expect, and expand the attack surface when combined with shell or LLM workflows.
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
Referenced artifact was not completely inspected
python3 scripts/dameng_tool.py check input.sql
This block enables inspection and, more importantly, execution of arbitrary Hermes skills via subprocess based on user input. That is a significant capability expansion unrelated to the declared purpose and can expose users to prompt injection, sensitive data access, or execution of risky downstream tooling through untrusted skills.
The skill documents capabilities that imply shell execution, filesystem access, environment-variable access, and network use, but it does not declare any explicit tool scope or permission boundaries. In an agent setting, this increases the chance of over-broad execution or user surprise, especially because the skill also supports DB connectivity and LLM-backed operations.
The documentation shows a command that passes database credentials on the command line, which can expose secrets via shell history, process listings, audit logs, and terminal recordings. In a development-assistant context, this is especially risky because users may copy-paste the example verbatim into shared or monitored environments.
The skill documents external LLM/API configuration and interactive chat usage but does not warn that prompts, code, SQL, or project data may be transmitted to third-party model providers. This can lead to accidental disclosure of proprietary source, credentials, schema details, or regulated data.
This markdown file presents all user-facing content in Chinese, including headings, descriptions, and recommendations, with no indication that the user can choose another language. The policy explicitly calls for flagging language or locale constraints when they are forced without user opt-in or documented justification.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| Line (pre-fix) | Hardcoded Value | Fix |
|---|---|---|
| `LLMClient.__init__` | `model_name='gpt-3.5-turbo'`, `provider='openai'` | New `_resolve()` method: env var → config.yaml → empty string |
| `_call_openai` | `api_base or "https://api.openai.com/v1"` | Empty-check with error message, no fallback URL |
| `_call_anthropic` | `api_base or "https://api.anthropic.com/v1"` | Same pattern |
| `call_llm` | `if self.provider == 'openai'` routing | Default route is openai-compatible for any non-anthropocustom provider |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| Line (pre-fix) | Hardcoded Value | Fix |
|---|---|---|
| `LLMClient.__init__` | `model_name='gpt-3.5-turbo'`, `provider='openai'` | New `_resolve()` method: env var → config.yaml → empty string |
| `_call_openai` | `api_base or "https://api.openai.com/v1"` | Empty-check with error message, no fallback URL |
| `_call_anthropic` | `api_base or "https://api.anthropic.com/v1"` | Same pattern |
| `call_llm` | `if self.provider == 'openai'` routing | Default route is openai-compatible for any non-anthropocustom provider |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
|---|---|---|
| `LLMClient.__init__` | `model_name='gpt-3.5-turbo'`, `provider='openai'` | New `_resolve()` method: env var → config.yaml → empty string |
| `_call_openai` | `api_base or "https://api.openai.com/v1"` | Empty-check with error message, no fallback URL |
| `_call_anthropic` | `api_base or "https://api.anthropic.com/v1"` | Same pattern |
| `call_llm` | `if self.provider == 'openai'` routing | Default route is openai-compatible for any non-anthropocustom provider |
### config.yaml
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
|---|---|---|
| `LLMClient.__init__` | `model_name='gpt-3.5-turbo'`, `provider='openai'` | New `_resolve()` method: env var → config.yaml → empty string |
| `_call_openai` | `api_base or "https://api.openai.com/v1"` | Empty-check with error message, no fallback URL |
| `_call_anthropic` | `api_base or "https://api.anthropic.com/v1"` | Same pattern |
| `call_llm` | `if self.provider == 'openai'` routing | Default route is openai-compatible for any non-anthropocustom provider |
### config.yaml
This markdown file contains only Chinese-language content and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience for a specific reason. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
技能清单描述将该技能定位为“以达梦数据库工具为核心,专注SQL Server→达梦迁移、代码安全扫描、知识库搜索”,但本文件把“测试用例生成、测试运行和覆盖率分析”描述为已集成的完整核心能力。这不是实现上述三项既有目标的显然必要细节,而是一个额外的功能域,导致技能宣称范围与文档描述的实际能力不一致。
The implementation materially exceeds the declared scope by acting as a general LLM assistant with outbound API access, while the manifest emphasizes Dameng migration, code scanning, and knowledge search. Scope drift is dangerous because users may trust the narrower description and unknowingly send sensitive prompts or trigger capabilities they did not expect.
User prompts are sent to external model providers whenever configured, but the interface does not warn users, obtain confirmation, or clearly identify the destination. In a developer/database assistant, prompts may contain source code, SQL, credentials, internal hostnames, or incident data, so silent transmission materially increases confidentiality risk.