Back to skill

Security audit

DAO Treasury Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed DAO treasury analysis tool that only queries DeFiLlama for user-requested protocol data.

Before installing, understand that running the tool contacts DeFiLlama and reveals which protocol slugs you query. It does not appear to install dependencies, store data, access credentials, or modify your system.

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
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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill description indicates network access to DeFiLlama, but the manifest does not declare any explicit tool scope or allowed-tools restriction. That creates an over-privileged/under-specified execution model where a host agent may permit broader network-capable behavior than users or platform policy expect, reducing transparency and making abuse or accidental expansion of external access harder to detect.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/treasury_tracker.py (reported line 36)May include surrounding context.

python
import urllib.request
import urllib.error

TREASURY_URL = "https://api.llama.fi/treasury/{slug}"
PROTOCOLS_URL = "https://api.llama.fi/protocols"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/treasury_tracker.py (reported line 37)May include surrounding context.

python
import urllib.request
import urllib.error

TREASURY_URL = "https://api.llama.fi/treasury/{slug}"
PROTOCOLS_URL = "https://api.llama.fi/protocols"