ClawHub
Back to skill

Security audit

nansen-token-screener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Nansen token-research workflow that uses authenticated CLI access and may incur paid API charges, but the sensitive behavior is described and fits its purpose.

Install only if you intend to use Nansen for token research and are comfortable giving the CLI account-level API access. Check your Nansen wallet/payment limits before running batch, paginated, or flow-intelligence queries because repeated calls may spend credits or funds.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description is broad enough to trigger on ordinary user requests about tokens, trends, or what is hot, which can cause the agent to invoke this skill in more situations than the user specifically intended. Because this skill can access authenticated research functions and may indirectly lead to paid API activity, overbroad routing increases the risk of unintended credentialed or billable actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill acknowledges automatic x402 payment behavior, including repeated charges inside loops, but the warning is buried in authentication prose rather than placed immediately before the suggested commands. That creates a realistic risk that an agent will run discovery workflows or iterative queries without surfacing clear user consent for potentially repeated spending.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.