ClawHub
Back to skill

Security audit

Renzo Protocol

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed read-only Renzo data query helper that sends requested query parameters to Renzo's public MCP endpoint without local file access or persistence.

Install only if you are comfortable sending Renzo query parameters, and any Ethereum address you ask about, to Renzo Protocol's MCP server. The reviewed artifacts do not request credentials, store data locally, or perform transactions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly instructs use of a Bash helper script (`renzo-mcp.sh`) but does not declare any `permissions` or `allowed-tools` scope to constrain shell execution. That creates an avoidable trust gap: a host may permit broader shell access than intended, and users/reviewers cannot tell from the manifest what execution capabilities are required or restricted.

External Transmission

Medium
Category
Data Exfiltration
Content
params: { name: $name, arguments: $args }
  }')

RESPONSE=$(curl -s -f --max-time 30 -X POST "$MCP_URL" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d "$PAYLOAD" 2>&1) || {
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.