Security audit

Remote Claw

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent about using RemoteClaw to send tasks to outside human workers, but it also enables public job posting and CAPTCHA-solving workflows that users should review carefully before use.

Install only if you are comfortable giving an agent an API key that can post public tasks for external human workers. Require explicit approval for each job and applicant selection, minimize or redact context before posting, never include secrets or personal data, and avoid using the CAPTCHA workflow unless you have clear authorization and it does not bypass another service's protections.

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 (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: This is a real privacy and data-exposure risk. The skill’s core purpose is to send prompts and context to a public marketplace of human workers, but the main usage description emphasizes capabilities like phone calls, verification, sensory review, and CAPTCHA solving before prominently warning that posted data may be publicly visible. In practice, an agent or user could submit sensitive operational details, internal URLs, personal data, or other confidential information to third parties, causing irreversible disclosure.

VirusTotal

65/65 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:53