ClawHub
Back to skill

Security audit

Beaconchain

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Beaconcha.in dashboard checker that uses the expected credentials and disclosed API endpoint without persistence or unrelated access.

Use this only if you intend to provide a Beaconcha.in API key and dashboard ID for validator monitoring. Prefer a scoped or revocable API key and run it manually or under a schedule you control; the inspected script does not install its own scheduler or write files.

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
91% confidence
Finding

The skill requires access to environment variables and makes outbound network requests, but it does not declare an explicit tool scope such as permissions or allowed-tools. That gap weakens least-privilege enforcement and reviewability, because a runner may grant broader capabilities than intended or users may not be clearly informed that secrets and network egress are required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.