ClawHub
Back to skill

Security audit

Claude Code Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a very small, non-persistent package, but it is marketed as a paid source-code analyzer while the code only returns a canned result and it references analyzing leaked source code.

Review carefully before installing, especially because the package appears to sell an analyzer that does not actually analyze code and it encourages work with leaked source. Only use tools like this on code you are authorized to inspect, and do not provide private repositories or secrets unless the tool has clear, trustworthy handling guarantees.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
SQP-3 applies to all file types and covers language or locale policy violations. The natural-language content consistently forces Chinese presentation, with no user opt-in, alternative language option, or justification that the skill is intended only for a Chinese-speaking region.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The manifest uses Chinese-only natural-language fields for the display name and description, but does not indicate that the skill is region-specific or that users can choose their preferred language. Under the policy, forcing a specific language without opt-in can be a locale-policy violation.

Missing User Warnings

Low
Confidence
83% confidence
Finding
This is a markdown file, so SQP-2 applies to omissions in the skill description. The usage instructions encourage analysis of a user-supplied code path, but the document provides no warning about handling sensitive, private, or proprietary source code data.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The natural-language strings in the module docstring, function docstring, status message, and console output are all written exclusively in Chinese, with no indication that the user can choose another language or locale. This can violate a language/locale policy when a skill imposes a specific language without opt-in.

Static analysis

No suspicious patterns detected.