ClawHub
Back to skill

Security audit

PumpView — Solana Trading & Live Data

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PumpView trading integration that uses external PumpView APIs and local wallet signing, with clear instructions to preserve user approval and protect secrets.

Install only if you intend to use PumpView for Solana trading or paid trade data. Treat API keys, signed transaction bytes, wallet signatures, invoice IDs, and trade details as sensitive, and review every wallet prompt, slippage value, fee, tip, destination, and payment before signing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill instructs the agent to connect to an external hosted API and MCP endpoint, which can transmit trading intent, wallet-linked metadata, API keys, and signed transaction material outside the local environment. In a trading skill this is expected functionality, but it still creates real data exfiltration and third-party dependency risk if the endpoint is compromised, spoofed, or used without strict secret-handling controls.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
# PumpView trading

Use the hosted service at `https://api.pumpview.fun`. MCP endpoint:
`https://api.pumpview.fun/mcp/?pv_source=clawhub` (Streamable HTTP, Bearer API key).
Public discovery and `get_trading_config` need no key. If available, call
`get_onboarding_instructions` to obtain the current access workflow and links.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 15)May include surrounding context.

md
Read [the integration reference](references/workflow.md) for wallet onboarding,
signed submission, error recovery, or paid live data. Current authoritative
schemas: https://api.pumpview.fun/v1/openapi.json and
https://pumpview.fun/developers/quickstart.md.

## Record the acquisition source

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.