Security audit

On-chain Token Diligence

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent crypto due-diligence helper, but it tells agents to make paid x402 cryptocurrency requests without explicit approval or spending limits.

Install only if you are comfortable with an agent calling paid crypto-data endpoints. Use a dedicated low-balance x402 wallet, require confirmation before every paid request, verify the exact amount, chain, asset, recipient, and host, and set strict session and daily spending limits.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:17
Finding: Paid x402 Requests Lack Explicit User Authorization and Spending Limits
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description says to use the skill whenever evaluating a token, screening a launch, sizing a trade, or answering whether a token is safe, including the natural-language phrase "is this token safe / legit / a rug". These triggers are broad and overlap with ordinary conversation, and the file does not provide narrower activation constraints or negative examples to prevent unintended invocation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.