Security audit

Baidu Map Harmonyos SDK（百度地图官方鸿蒙 SKills）

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Baidu Maps HarmonyOS development guide, but it tells agents to make broad dependency and source-code migrations automatically without asking the user first.

Install only if you are comfortable with the agent changing dependencies and imports across the project. Before using it, require explicit approval for package migrations, pin @bdmap package versions, review lockfile and source diffs, and run builds in a workspace without unrelated secrets.

A.I.G

Vulnerability Patterns

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
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:79
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: references/guidelines/package-management.md:79
Finding: Automatic Repository-Wide Dependency Migration Without User Approval
Content: View full analysis
from '' from '@bdmap/map' -> from '' from '@bdmap/search' -> from '' from '@bdmap/util' -> from '' ``` It concludes by executing: ```bash ohpm install && hvigorw assembleHap --mode module -p product=default -p buildMode=debug --no-daemon ``` The associated instructions explicitly require the Agent to perform this migration automatically without additional user confirmation. ### Technical Analysis The Skill converts a feature request into authorization for repository-wide mutation. It instructs the Agent to: 1. Remove existing dependencies. 2. Install a different dependency bundle. 3. Scan all `.ets` and `.ts` source files. 4. Replace import paths throughout the project. 5. Execute package installation and a build. The workflow does not require an explicit migration confirmation, a clean working-tree check, a backup, a reviewed diff, a bounded file list, or an automatic rollback mechanism. A broad textual import replacement may affect files outside the intended feature, including tests, tools, generated files, examples, or modules with distinct dependency constraints. Build validation detects only some syntactic and type-level regressions. It does not establish behavioral compatibility, prevent unintended source modifications, or guarantee restoration after a failed migration. ### Attack Path 1. A user requests a feature in ...[truncated 1591 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (325)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.
md
- 详细规则与示例见：[代码规范](references/guidelines/coding-standards.md)。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.
md
- 详细规则与示例见：[代码规范](references/guidelines/coding-standards.md)。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 317)May include surrounding context.
md
- 详细规则与示例见：[代码规范](references/guidelines/coding-standards.md)。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.
md
- 生成或修改示例代码时，优先使用本 Skill 资产中约定的图片名，并保持与 [assets](references/assets.md) 表格中的用途一致或相近。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 299)May include surrounding context.
md
- 生成或修改示例代码时，优先使用本 Skill 资产中约定的图片名，并保持与 [assets](references/assets.md) 表格中的用途一致或相近。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 118)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 127)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 128)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 132)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.
md
- **示例与 API 使用**：回答与实现时，应优先参考本目录下 `references/reference.md` 中给出的示例代码与调用方式，在此基础上按业务场景做适配，避免自创与 SDK 不一致的用法。

Static analysis

No suspicious patterns detected.