ClawHub
Back to skill

Security audit

Raydium

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Raydium pool-risk analysis skill with no code execution, wallet access, persistence, or external data access, though some trigger phrases are broader than ideal.

This skill is reasonable to install if you want Raydium LP risk analysis, but treat its output as decision support rather than financial advice. Be aware that broad triggers may activate it for generic liquidity questions, so confirm the pool and protocol context before relying on recommendations.

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
Confidence
95% confidence
Finding
The trigger phrase at line 29 ('pool depth') is broad enough to match many ordinary DeFi or trading questions that are not clearly intended to invoke this specific skill. Overbroad activation can cause unintended skill routing, which may inject specialized financial guidance into unrelated contexts and reduce user control over which skill is used.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The triggers on lines 30-32 include generic phrases like 'concentrated liquidity risk' and 'liquidity audit' that can overlap with broad user requests across many protocols and contexts. In a financial decision-support skill, accidental invocation is more concerning because it may provide protocol-specific deployment guidance where the user did not explicitly request this skill.

Static analysis

No suspicious patterns detected.