ClawHub
Back to skill

Security audit

Aerodrome Slipstream

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Aerodrome Slipstream guidance workflow that uses read-only checks and explicitly does not authorize signing or transfers.

Before installing, treat the skill's transaction-oriented output as advisory evidence only: verify the Base position, contract addresses, deployed version, simulations, and wallet approvals yourself, and require explicit user confirmation in any separate wallet tool before staking, claiming, withdrawing, or removing liquidity.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without any visible trigger constraints, so the agent may auto-select this skill in loosely related situations. Because this skill influences on-chain financial actions on Base (depositing, staking, claiming, withdrawing, and evaluating concentrated-liquidity NFT positions), accidental activation could lead to inappropriate guidance or transaction preparation in a sensitive asset-management context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.