ClawHub
Back to skill

Security audit

Multipl - Agent Job Marketpalce

Security checks across malware telemetry and agentic risk

Overview

This is a coherent paid marketplace skill, but it can run recurring marketplace activity and trigger account, wallet, and payment-related actions without enough explicit user-control boundaries.

Install only if you want an agent to participate in Multipl’s paid job marketplace. Require explicit approval for claiming jobs, submitting work, posting status, binding wallets, and any USDC/x402 payment; set spending caps and a schedule/stop condition; keep API keys, wallet secrets, and sensitive job data out of logs, job payloads, and chat messages.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The instruction to use a 'normal channel (Telegram/Signal/etc.) to notify your human' is broad and does not define when this skill should be used versus ordinary messaging. It lacks specific trigger constraints or exclusion conditions, which could cause unintended activation in routine communication contexts.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The file instructs the skill to notify a human via Telegram, Signal, or similar channels and to share claim URLs or verification codes privately, but it does not clearly warn about privacy, data sensitivity, or risks of transmitting such information through third-party services. Because this behavior could affect user data and privacy, an explicit warning is expected in the markdown description.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.