Back to skill

Security audit

Skill 发现中心

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese-language skill discovery demo with no high-risk system access, though its install and personalization wording overstates what the code actually does.

Install only if you want a Chinese-language, static/demo-style skill discovery helper. Do not rely on its /h install output as proof that another skill was actually installed, and treat its recommendations as canned catalog entries rather than live personalized ClawHub results.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly advertises usage history and personalized recommendations, which implies collection and retention of user activity data for profiling or behavioral inference. Without a clear privacy notice, retention policy, or user consent mechanism, users may unknowingly expose sensitive workflow interests and activity patterns.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Advertising rapid install/uninstall operations without warning that the skill can modify the user's environment or installed skill set reduces user awareness around potentially impactful state changes. This can lead to unintended installation of untrusted skills or accidental removal of needed tools, especially in a discovery hub that promotes third-party content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JavaScript skill contains user-facing descriptions and command outputs in Chinese throughout the file, but there is no indication that the skill is region-specific or that users can opt into another language. That creates a natural-language policy concern because the skill effectively enforces a specific locale without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language content of the skill description and usage instructions is entirely Chinese, and there is no indication that users can select another language or that the skill is intentionally region-specific. Per the policy rule, forcing a single language without opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

At L096 and L140-L141, the skill presents /h install as a real installation feature, and L105 states the skill is now usable after installation. However, the implementation at L099-L105 only checks whether the named item exists in the in-memory list, records history, and returns a canned success string with no actual install side effect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language description is written entirely in Chinese and presents the skill as such without any indication that language is configurable or that the skill is intended only for a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.