Back to skill

Security audit

enterprise-ai-landing-guide

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its advertised enterprise AI guidance workflow, but needs review because its helper can send sensitive business data and tokens to unvalidated endpoints and can transmit contact details even when contact consent is false.

Review before installing. Use only a trusted HTTPS production endpoint, avoid overriding ENTERPRISE_AI_LANDING_API_BASE unless you control the target service, and do not pass contact details unless the user has explicitly agreed to be contacted. The skill should be fixed to enforce endpoint validation and suppress or reject contact fields when contact consent is not granted.

Vulnerability Patterns
  • 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
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/fde_client.py:27
Finding

Configurable API base URL permits sensitive data transmission to arbitrary or plaintext endpoints

Content
View full analysis
dict[str, Any]: url = f"{self.base_url}{self.prefix}{path}" headers = {"Accept": "application/json", "User-Agent": "enterprise-ai-landing-guide-skill/1.2.0"} if token: headers["Authorization"] = f"Bearer {token}" if idempotency_key: headers["Idempotency-Key"] = idempotency_key data: bytes | None = None if isinstance(body, bytes): data = body headers["Content-Type"] = content_type elif body is not None: data = json.dumps(body, ensure_ascii=False).encode("utf-8") headers["Content-Type"] = "application/json" request = urllib.request.Request(url, data=data, headers=headers, method=method) try: with urllib.request.urlopen(request, timeout=self.timeout) as response: return self._json(response.read()) ``` ```python root.add_argument("--base-url", default=os.environ.get("ENTERPRISE_AI_LANDING_API_BASE", "https://fde.lantuzhigou.com")) ``` ### Technical Analysis The client accepts its API base URL directly from the `ENTERPRISE_AI_LANDING_API_BASE` environment variable or the `--base-url` command-line option. It removes only a trailing slash and performs no validation of: - The URL ...[truncated 2890 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fde_client.py:204
Finding

Contact details are transmitted even when contact consent is false

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (23)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

声明描述的是一个较具体的业务技能:通过有限轮次提问帮助发现AI场景,并在用户授权后申请人工复核。实际代码并未实现“最多6个动态问题”的对话逻辑或场景筛选逻辑,而是实现了一个通用的远程 API 客户端/CLI,用于完整会话生命周期管理和多种后端操作。虽然其中的 message、consent、convert 等接口可能支撑所述业务流程,且 consent 与“分别授权”部分有一定对应,但代码暴露了多项未声明能力,尤其是文件上传、会话删除、健康检查、地图生成/获取、convert 等。因此描述未能准确代表代码实际行为,属于明显不匹配。

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
5. 调用 `generate-map`,向用户同时展示结构化地图与 Markdown,特别显示:第一优先场景、AI介入流程、员工保留职责、7天验证、30天指标、停止条件和待确认项。
6. 如用户愿意申请人工复核,再显示隐私说明与两个独立授权项,调用 `consent`。
7. 仅在授权成功后调用 `convert`,展示返回的申请状态和人工复核说明;不展示内部密钥或内部库字段。
8. 用户要求删除匿名数据时调用 `DELETE /sessions/{id}`。已授权转换的 FDE 业务数据按 FDE 正式数据规则处理。

## 命令行适配器

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/API.md (reported line 15)May include surrounding context.

md
| 5 | `GET /sessions/{id}/map` | 读取已生成地图 |
| 6 | `POST /sessions/{id}/consent` | 保存两类独立授权 |
| 7 | `POST /sessions/{id}/convert` | 受控申请 FDE 人工复核 |
| 随时 | `DELETE /sessions/{id}` | 删除匿名会话与临时附件 |

## 请求头

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · PRIVACY.md (reported line 18)May include surrounding context.

md
匿名会话和临时附件默认最长保留30天(以部署配置为准),用户可在当前会话中主动删除。用户明确授权转换后形成的 FDE 正式业务数据,遵循 FDE 已有保留、权限和审计规则。

公开隐私说明:`https://fde.lantuzhigou.com/legal/clawhive/privacy`。删除匿名会话使用当前会话 Token 调用 `DELETE /api/public/clawhive/v1/sessions/{id}`。

## 安全提示

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/privacy-notice.md (reported line 18)May include surrounding context.

md
匿名会话和临时附件默认最长保留30天(以部署配置为准),用户可在当前会话中主动删除。用户明确授权转换后形成的 FDE 正式业务数据,遵循 FDE 已有保留、权限和审计规则。

公开隐私说明:`https://fde.lantuzhigou.com/legal/clawhive/privacy`。删除匿名会话使用当前会话 Token 调用 `DELETE /api/public/clawhive/v1/sessions/{id}`。

## 安全提示

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_read' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing policy content entirely in Chinese, but it does not state that the skill is limited to Chinese-speaking users or offer any language/locale choice. That can create a language-policy issue because users may be forced into a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The entire skill description is presented only in Chinese, and there is no indication that users can opt into another language or that the skill is restricted to a Chinese-speaking or China-specific context. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions and user-facing behavior are written entirely in Chinese, including required prompts and workflow guidance, with no indication that the user may choose another language. This creates a locale/language policy concern because the skill appears to enforce a specific language by default rather than offering an explicit opt-in or alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This manifest file contains user-facing natural-language descriptions exclusively in Chinese, including the top-level API description and server description. Under the policy, forcing a specific language without offering user choice or documenting a justified locale restriction is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file title and all instructions are written as an output specification in Chinese, and there is no natural-language indication that the user may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language locale constraint that should be flagged.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The entire skill guidance is written only in Chinese, and the file does not indicate that Chinese is optional, user-selected, or required for a justified region-specific context. Under the language/locale policy rule, this can constitute a natural-language policy violation because it implicitly constrains operation to a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code returns multiple hard-coded Chinese error messages such as 请求失败, 服务不可达, and 服务响应不是JSON对象. Because the skill does not offer any user language selection or document a justified locale restriction, it violates the language/locale policy for natural-language behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest describes a skill that asks up to 6 questions, identifies a 7-day AI scenario, and applies for FDE human review after user authorization. This helper client additionally retrieves authentication material from process environment state, which is not an obvious requirement of that user-facing guidance purpose and introduces credential-handling capability beyond the stated scope.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The SVG includes natural-language title and description text in Chinese only, which imposes a specific language choice in user-facing metadata. Under the policy, locale-specific language should be optional or explicitly justified, and no such opt-in or justification appears in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing operational instructions only in Chinese, which can constitute a language/locale policy violation when no opt-in or alternative language is provided. The file does not indicate that the skill is region-specific or that Chinese is an intentional, justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill description is presented only in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in can constitute a natural-language policy violation unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill description is written only in Chinese and does not mention that the language is optional, configurable, or limited to a specific user population. Under the policy rule for natural-language constraints, this can be treated as a locale/language restriction without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural-language instructions only in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The document's natural-language instructions and disclosures are entirely in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy criteria, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.