Back to skill

Security audit

周易占卜 - ZhouYi Divin

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese-language ZhouYi divination skill that processes user-entered birth details and questions without network access or persistence.

Install only if you are comfortable using a Chinese-language local command-line divination tool and entering birth details or personal questions that may be shown in terminal output, shell history, or saved JSON if you redirect output. I found no evidence of network access, credential use, destructive actions, or hidden execution.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

该代码块是一个八字排盘模块,核心行为围绕出生年月日时计算年柱、月柱、日柱、时柱,以及五行分布、喜用神和简化大运分析。它与声明中的“八字排盘”部分一致,但声明强调的是“基于《周易》的完整占卜系统”,并明确包括“铜钱起卦 + 八字排盘 + 综合解读”。从提供的代码看,没有任何铜钱起卦、卦象生成、爻变、六十四卦解析等《周易》占卜功能,也没有跨多种占卜方式的完整系统实现。因此描述明显宽于实际代码能力,属于能力声明与实际行为不符。

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/divine.py (reported line 202)May include surrounding context.

python
"judgment": changing_hexagram["judgment"],
            "image": changing_hexagram["image"]
        }
    
    return result

def oracle_with_bazi(result, bazi_report=None):
    """AI Oracle 诠释(支持八字结合)"""
    mh = result["main_hexagram"]
    
    print("\n" + "=" * 60)
    print("📖 《周易》综合解读报告")
    print("=" * 60)
    
    print(f"\n🙋‍♀️ 你所问:{result['question']}")
    
    print(f"\n═══════════════ 🎯 本卦信息 ═══════════════")
    print(f"   卦名:{mh['name']} (第{mh['number']}卦)")
    print(f"   卦象:{mh['trigrams']}")
    print(f"   卦辞:{mh['judgment']}")
    print(f"   大象:{mh['image']}")
    
    if result.get("changing_lines"):
        ch = result["changing_hexagram"]
        print(f"\n═══════════════ 🔄 变卦信息 ═══════════════")
        prin

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation is entirely in Chinese and does not indicate that other languages are supported or that the user can opt into Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill as Chinese-language only, with no indication that users can choose another language or locale. This is a natural-language locale constraint that is not explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The user-facing documentation and examples are entirely in Chinese, including prompts, parameter descriptions, and safety notes, which effectively imposes a single language on users. The file does not offer an alternative language, opt-in, or a documented justification for a locale-specific restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This Python file contains natural-language descriptions and printed report text entirely in Chinese, including the module docstring and all user-facing report output. Under the policy, forcing a specific language without user opt-in is a language/locale policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script collects highly sensitive personal data, including birth date/time, gender, and potentially intimate divination questions, then immediately displays and processes them without any privacy notice, consent flow, minimization, or retention guidance. In an agent skill context, users may not realize this information could be logged by the host environment, terminals, wrappers, or orchestration layers, creating a real privacy exposure.

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 only Chinese-language instructions and support text, which can amount to a language/locale policy violation if the skill is expected to accommodate users without forcing a specific language. There is no visible note offering alternative languages or asking for user preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

User-facing strings, prompts, help text, and outputs are entirely in Chinese, which enforces a specific language/locale for all users. The policy allows locale constraints only when documented and justified or when the user is offered a choice, neither of which is present here.

Content

No source excerpt is available for this finding.