ClawHub
Back to skill

Security audit

Galleon DeFi Security Token Diligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only token diligence workflow with a bounded helper and clear warnings about evidence limits.

Install only if you are comfortable letting the agent use your existing read-only blockchain data providers and possibly consume provider quota. Do not provide wallet keys or broadcast-capable endpoints; treat reports as evidence-bounded diligence, not a guarantee that a token is safe or sellable.

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
98% confidence
Finding

The skill advertises comprehensive token security diligence, but the implemented behavior appears limited to a bounded metadata/code snapshot and does not substantively verify key risk areas such as launch allocations, liquidity custody, sellability, treasury flows, or privileged controls. In a security-review context, this can mislead users into relying on an incomplete assessment and making high-risk decisions under a false sense of coverage.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill expects access to networked RPC providers and possibly environment-backed credentials, but it does not declare an explicit tool/permission scope. That creates a governance and review gap: operators cannot clearly constrain or audit what capabilities the skill may use, increasing the chance of over-broad data access or unintended external calls in an adversarial or misconfigured runtime.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.