ClawHub

PlayCanvas

Security checks across malware telemetry and agentic risk

Overview

This is mostly a PlayCanvas documentation skill, but it contains a real-looking bearer token example and guidance for mutating or deleting cloud assets without strong user-confirmation safeguards.

Review before installing if agents may operate on real PlayCanvas projects. Replace or remove the bearer token example, require explicit approval before delete/force/overwrite/merge/publish API calls, use least-privilege PlayCanvas tokens, revoke any exposed token, and pin CDN or package versions for production projects.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The documentation describes a destructive delete operation, including a force parameter, without warning that deletion may permanently remove project assets or break references. In an agent skill context, this omission increases the chance an automated system invokes deletion without surfacing the data-loss risk to the user.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The upload endpoint states that subsequent calls replace the previous file, but it does not prominently warn that existing content will be overwritten. In an agent-assisted workflow, that can lead to accidental loss of prior asset files if the agent updates the asset in place without confirmation or backup guidance.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The documentation recommends loading executable JavaScript modules directly from a third-party CDN using mutable @latest URLs, without any warning about supply-chain trust, version pinning, or integrity verification. If the CDN, package, or network path is compromised, consumers may unknowingly execute attacker-controlled code in their application.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal