ClawHub
Back to skill

Security audit

Dpa

Security checks for vulnerabilities and agentic risk

Overview

This is a static GDPR/DPA reference skill whose bundled shell script only prints legal reference text and does not access data, network, credentials, or persistent system features.

Before installing, treat the content as general legal-reference material rather than legal advice, and review the publisher/source if you require authoritative or jurisdiction-specific DPA guidance. The executable surface is low impact based on the inspected script, but a static markdown-only version would be even narrower.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill advertises executable shell-based commands and likely code capabilities, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where an agent or runtime may permit broader shell or network access than intended, increasing the risk of command execution or outbound access beyond the skill's documented purpose. In this legal-reference context, shell/network capability is not obviously necessary for a static GDPR/DPA reference skill, which makes the mismatch more concerning.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.