ClawHub
Back to skill

Security audit

WachAI-x402

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed paid DeFi risk-analysis helper that uses AWAL/x402 for small capped payments and does not show hidden, destructive, or unrelated behavior.

Install only if you are comfortable using AWAL custody and paying 0.01 USDC on Base for each token analysis. Keep the default max-amount cap, do not provide private keys or seed phrases, and treat any request to raise spend limits as a separate explicit decision.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises that payment is automatic via x402/AWAL and gives command flows that lead directly to a paid network action, but it does not require an explicit user confirmation immediately before the chargeable verify-risk call. In an agent setting, this can cause unintended spending or surprise charges, especially because the skill is framed as a routine analysis tool and the paid step is operationally close to setup/readiness checks.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
## Absolute Prohibitions for OpenClaw

- Do not use or suggest `wallet create`, `wallet import`, or `wallet.json`.
- Do not ask user for private key or seed phrase.
- Do not increase spend cap silently.
- Do not claim analysis success when output parsing failed.
- Do not suppress AWAL raw errors when diagnosis is needed.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill imposes a branded, mandatory rule set on the agent ('OpenClaw Hard Rules (Non-Negotiable)') without user opt-in, which is a form of agent-behavior override. While many of the rules are safety-positive, embedding non-negotiable behavioral control in skill content can conflict with higher-priority user or platform policies and creates a precedent for instruction capture by untrusted skill authors.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.