ClawHub
Back to skill

Security audit

Clarity Changes

Security checks for vulnerabilities and agentic risk

Overview

This skill only reads public Clarity Protocol change and leaderboard data, with an optional disclosed API key for higher rate limits.

Before installing, understand that running the scripts will contact clarityprotocol.io and may send CLARITY_API_KEY as an X-API-Key header if that environment variable is set. The reviewed artifacts do not modify local files or remote data.

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
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The code matches the 'recent changes' portion of the description: it accepts a --since timestamp, optional type filter, calls the /changes endpoint, and outputs recent findings/annotations. However, the declared description also says the skill can view an agent leaderboard/top contributors, which is not present anywhere in this code chunk. There are no undeclared dangerous capabilities or inconsistent resource accesses; the mismatch is that the description overstates functionality relative to the supplied code.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill declares internet access and optional use of an environment variable API key, but it does not define an explicit tool scope such as permissions or allowed-tools. That creates ambiguity about what runtime capabilities the skill is expected to use and can enable broader-than-necessary network or environment access in hosts that rely on manifest scoping for enforcement.

Static analysis

No suspicious patterns detected.