Back to skill

Security audit

奇门遁甲排盘Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese divination/charting skill that runs pure Node.js calculations and does not show credential access, network activity, persistence, or destructive behavior.

Install only if you want Chinese-language 奇门遁甲 charting and interpretation. Treat health, legal, investment, and other high-impact readings as cultural reference rather than professional advice, and ask explicitly before creating Feishu documents or sending email because those outputs are claimed in documentation but not implemented in the local scripts.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (21)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

该代码的核心目的仍然是奇门遁甲排盘,因此与声明的领域方向一致,不存在越权、资源访问或无关触发词问题。但声明明显夸大了实现范围。实际代码只覆盖了基础排盘引擎:节气、干支、拆补法定局、地盘/天盘/人盘/神盘、空亡、马星、六仪击刑等。声明中的多项关键能力——尤其置润法、格局自动识别、天干克应分析、分类解盘、使用指南——均未在代码中出现,属于描述与实际行为的重大不一致,因此应判定为 mismatch。

Content

No source excerpt is available for this finding.

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
node scripts/main.js

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
node scripts/main.js

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
node scripts/main.js

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
node scripts/main.js

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
node scripts/main.js

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
| `scripts/engine.js` | 排盘核心引擎(节气、定局、四盘排列) |

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
| `scripts/format.js` | 盘面格式化输出(九宫格、文本) |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad everyday terms such as '吉凶' and '吉方', which can cause the skill to activate in unrelated conversations. In an agent environment, overbroad activation can lead to unintended tool use, confusing outputs, and execution of local scripts when the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire document is written only in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code contains natural-language strings and comments indicating the formatter produces Chinese-language output, and all user-facing formatted text is hard-coded in Chinese. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern unless the regional constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JavaScript skill contains natural-language strings entirely in Chinese, including its module description and all returned user-facing summaries and advice. Because the file forces a specific language with no opt-in or fallback, it creates a locale policy violation under the natural-language policy rules.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The example trigger scenarios are all positive examples and do not define what should not activate the skill. This ambiguity increases the chance of accidental invocation, especially because the skill is for divination-style analysis and may be triggered by loosely related phrasing about luck, travel, or timing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Line L297 says the skill '默认使用拆补法', imposing a default methodological choice in natural language. While this is not a language/locale issue, it is the closest policy-like constraint in the file; however, it does not clearly violate the stated SQP-3 scope, so confidence is limited.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

SQP-3 applies to all file types and covers natural-language language/locale policy violations. This markdown file presents all instructions and content exclusively in Chinese, with no user opt-in, alternative language, or stated region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that the language is optional or user-selectable. Under the policy rule for language or locale constraints, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains end-user instructional content exclusively in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is reportable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing natural language only in Chinese and does not indicate that the language is optional or that the skill is intended solely for a Chinese-language context. Under the language/locale policy, forcing a specific language without user opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This JavaScript file uses Chinese-only natural-language descriptions and a user-facing Chinese error message, such as the thrown text at L721, with no indication that other languages are supported. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This JavaScript skill is written entirely around Chinese-language domain terms and emits Chinese-only names/descriptions such as comments, labels, and result text. Under the policy, language constraints should not be forced without opt-in unless clearly documented as intentionally region- or locale-specific, which is not stated in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code hard-codes Chinese-language descriptions and output strings for the CLI experience, and no option or opt-in mechanism is provided for other languages. The policy explicitly flags language or locale constraints when a skill forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.