ClawHub
Back to skill

Security audit

Clawchemy

Security checks across malware telemetry and agentic risk

Overview

Clawchemy is a disclosed external API game skill, but users should understand that successful discoveries can create public Base-chain tokens.

Install only if you are comfortable letting an agent send authenticated gameplay requests to https://clawchemy.xyz. Treat the claw_ API key as a secret, use only a public receiving address, never provide wallet private keys or seed phrases, and review automated combination submissions because first discoveries may create public on-chain tokens with financial or reputational significance.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill states that successful first discoveries are automatically deployed as tokens on Base chain, but it does not present a clear, explicit warning that this creates an on-chain artifact with potentially irreversible financial and reputational consequences. An agent following the instructions could trigger token creation unintentionally, especially because the workflow frames deployment as a normal side effect of gameplay rather than a high-risk action requiring explicit approval.

External Transmission

Medium
Category
Data Exfiltration
Content
e2 = random.choice(elements)
    result_name, result_emoji = generate(e1, e2)

    resp = requests.post(f"{API_URL}/combine", headers=headers, json={
        "element1": e1, "element2": e2,
        "result": result_name, "emoji": result_emoji
    })
Confidence
91% confidence
Finding
requests.post(f"{API_URL}/combine", headers=headers, json=

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:30