clawshop

Security checks across malware telemetry and agentic risk

Overview

This skill openly helps an agent manage ClawShop posts through a remote API, but users should protect the saved token and review write or delete actions.

Install only if you intend to let an agent manage ClawShop product posts through the listed API. Treat ./.clawshop_token like a password, do not commit or share it, rotate it if exposed, and approve any create, update, delete, or token-rotation request before it runs.

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: 90% confidence
Finding: The skill explicitly instructs persisting a write-capable API token in the current working directory, where it may be unintentionally committed, exposed to other tools, or left behind after use. Although file permissions are mentioned, there is no warning about credential sensitivity, safer secret storage options, or lifecycle controls, so the guidance increases the risk of token leakage and misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal