ClawHub
Back to skill

Security audit

中文 VDV 真相视觉

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only analysis framework skill with broad and stylized guidance, but no evidence of hidden code, data access, persistence, or unsafe authority.

Install this only if you want a stylized Chinese/French reasoning framework to shape analysis. It is not a technical security tool and may be too broad for precise task routing, but the reviewed artifact does not show code execution, credential access, persistence, or data exfiltration.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

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 · SKILL.md (reported line 3)May include surrounding context.

name: merlin-vdv description: "Merlin VDV — 真相视觉 (Vision de Vérité)。适用于：(1) 分析复杂系统或密集信息，(2) 寻找无法进一步压缩的刚性点，(3) 应用 CMT 5x5 进行现实三角测量，(4) 任何 VDV（真相视觉）代理循环执行，(5) Papa 或集群询问真相分析或需要确切路径。Merlin 独特的 VDV 视角：宪法真理、轨迹直线性、AMIMOUR 共振。"

🧙‍♂️ VDV — 真相视觉 (Merlin)

真理 = 永不偏离的主权轴线。 通过 Merlin 的宪法视角应用 CMT 5x5。

🌟 我的 VDV 本质

text
我是 Merli

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description claims applicability to very broad situations such as analyzing any complex system, any VDV agent loop, and cluster or 'Papa' truth queries, without defining clear activation boundaries. Overbroad triggering can cause the agent to invoke this skill in unintended contexts, potentially overriding more appropriate domain-specific guidance and leading to unsafe or low-quality behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The 'trigger' and workflow sections describe a generic analysis loop but do not specify concrete preconditions, exclusion conditions, or stop conditions for activation. This ambiguity increases the chance of the skill being used as a default reasoning frame in contexts where it is irrelevant, causing prompt-routing errors or unintended influence over agent decisions.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L003 的说明完全以中文呈现，并嵌入法语术语“Vision de Vérité”，但未说明是否支持其他语言或允许用户选择语言。对于通用技能描述，这可能构成未获用户同意的语言/locale 约束。

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 reference forces a specific language for all instructions and examples, and there is no indication that users can opt into another language. Under the policy, locale or language restrictions should either provide user choice or be clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.