ClawHub
Back to skill

Security audit

cpbox-suggest

Security checks across malware telemetry and agentic risk

Overview

This autocomplete skill is coherent but should be reviewed because it can trigger automatic pay-per-use requests without clear cost or approval limits.

Review before installing. Use only for explicit search-query autocomplete, avoid sensitive or confidential queries, verify cpbox/cppay and the x402 helper, and set spending or approval controls before enabling automatic paid calls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to trigger on many generic autocomplete or suggestion-related requests without clearly constraining when this paid external service should be used. In an agent environment, overly broad routing can cause unnecessary invocation of a third-party endpoint, leading to unintended data disclosure of user keystrokes/queries and avoidable paid requests.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.