ClawHub
Back to skill

Security audit

Naval 视角

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only advisory skill for applying Naval Ravikant-style decision lenses, with a Chinese-language default that users should be aware of.

Install this if you want a Chinese-language Naval-style advisory lens. Non-Chinese users should expect localized guidance gaps, but the artifact is read-only and does not appear to access private data, run code, or change the environment.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill sets Chinese as the default output language in its default contract, which can override or steer responses away from the user's expected language when no explicit preference was provided. This is a real policy/quality issue because it reduces user control and can cause misunderstanding, though it does not by itself enable code execution, data exfiltration, or privilege abuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The display name and short description are written in Chinese, while the default prompt is hard-coded in English. This creates a language-policy concern because the skill appears to impose a mixed locale experience without any documented user opt-in or language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file content is entirely in Chinese and does not offer any language-choice mechanism or document a locale-specific requirement. This can exclude or mislead users who do not read Chinese, causing them to miss important safety and scope limitations in the skill boundaries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s guidance is entirely written in Chinese and defines the expression style in that language, with no indication that users may opt into another language or that the skill is intentionally limited to a Chinese-language context. This creates a natural-language locale constraint that may conflict with organizational policy requiring language choice or explicit justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.