Security audit

amis-helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only helper for generating Baidu amis admin-page JSON, with data-changing examples that are disclosed and aligned with that purpose.

Install this if you work with amis 6.x and are comfortable with Chinese documentation. Review any generated JSON before deploying it, especially delete/import/export actions, API URLs, auth-bearing downloads, and ENV-derived variables, because those can affect real application data once wired to production endpoints.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (24)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.
md
| C-01 | perPageAvailable 放 crud 顶层 | references/crud.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.
md
| C-01 | perPageAvailable 放 crud 顶层 | references/crud.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.
md
| C-01 | perPageAvailable 放 crud 顶层 | references/crud.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.
md
| D-01/D-04/D-06 | 弹层提交：close:false+submitSucc 关窗，禁 loadingOn/onEvent.submit | references/dialog-actions.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.
md
| D-01/D-04/D-06 | 弹层提交：close:false+submitSucc 关窗，禁 loadingOn/onEvent.submit | references/dialog-actions.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.
md
| D-01/D-04/D-06 | 弹层提交：close:false+submitSucc 关窗，禁 loadingOn/onEvent.submit | references/dialog-actions.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.
md
| D-01/D-04/D-06 | 弹层提交：close:false+submitSucc 关窗，禁 loadingOn/onEvent.submit | references/dialog-actions.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.
md
| D-01/D-04/D-06 | 弹层提交：close:false+submitSucc 关窗，禁 loadingOn/onEvent.submit | references/dialog-actions.md §1 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.
md
| F-03 | autoComplete 用对象或字符串 URL（不能写 true） | references/form-controls.md §3 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.
md
| F-03 | autoComplete 用对象或字符串 URL（不能写 true） | references/form-controls.md §3 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.
md
| F-03 | autoComplete 用对象或字符串 URL（不能写 true） | references/form-controls.md §3 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.
md
| F-03 | autoComplete 用对象或字符串 URL（不能写 true） | references/form-controls.md §3 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.
md
| A-02 | 非标准响应用 adaptor 转 status（防失败被当成功） | references/data-source.md §2 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.
md
| A-02 | 非标准响应用 adaptor 转 status（防失败被当成功） | references/data-source.md §2 |

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.
md
| 不生效 / 没反应 / 报错 / 排查 / 为什么 | references/pitfalls.md |

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger matrix includes very broad, common phrases such as 'form', 'api', '报错', and '为什么', which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance the agent will load and prioritize this skill outside its intended amis-specific context, creating prompt-scope hijacking risk and degrading routing safety.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This file contains user-facing instructional content exclusively in Chinese, starting at L001 and continuing throughout the document. Under the policy, forcing a specific language without user opt-in or a documented justification 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: 90% confidence
Finding: This markdown file presents all user-facing instructions in Chinese, which can impose a language choice on users without opt-in. The policy allows locale constraints only when explicitly offered as a choice or clearly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file contains user-facing documentation exclusively in Chinese, including headings, scope notes, and rule descriptions, with no indication that users may choose another language. Under the language/locale policy, forcing a single language without opt-in can be a natural-language policy concern unless the constraint is explicitly justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: This is a JSON manifest file, so vague-trigger checks apply. The activation wording uses generic terms like "Bind Items" and "Select Items" without documenting when this action should be used versus avoided, which can make invocation scope ambiguous in systems that map labels/descriptions to skill selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: This markdown file contains user-facing instructions exclusively in Chinese, and there is no indication that the skill is region-specific or that users may opt into another language. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: At L62, the documentation explicitly lists ${ENV.xxx} and ${LC_LOCALE} as available variable sources, which indicates the skill can read environment-derived values. The markdown does not include any caution that environment variables may contain sensitive data or that users should avoid exposing secrets unintentionally.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown provides implementation patterns for destructive deletion and file export/network actions, but it does not explicitly warn readers about the user-impact risks of deleting records or exporting data. Under the markdown-specific SQP-2 criteria, skills/docs should disclose behaviors that can affect user data, privacy, or system integrity.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The title and introductory text are entirely in Chinese, and the file provides no indication that language selection is optional or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy, natural-language content that effectively forces a specific language without user opt-in should be flagged.
Content: No source excerpt is available for this finding.