ClawHub
Back to skill

Security audit

claude-md

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped CLAUDE.md maintenance template with no hidden execution, network use, or credential handling.

Review the resulting CLAUDE.md before relying on it, because it can influence future agent behavior in the repository. The package itself is simple and scoped, with no evidence of hidden commands, credential access, network calls, or background persistence.

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 (1)

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The manifest sets `language: en`, which expresses a fixed language preference. The file does not offer a user language choice or explain a region- or compliance-based reason for restricting the skill to English, so this is a natural-language policy concern under the locale policy rule.

Static analysis

No suspicious patterns detected.