ClawHub
Back to skill

Security audit

ClawDiscover

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ClawDiscover service-discovery integration, but users should intentionally configure its external calls, paid endpoints, webhooks, and recurring checks.

Install this only if you want your agent to query ClawDiscover. Keep paid x402 endpoints, service submissions, webhook registration, and recurring heartbeat checks under explicit user control, and do not submit secrets, private URLs, or privileged internal webhook endpoints.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The webhook subscription example instructs users to send an agent identifier and external callback URL to a third-party service without any warning about data disclosure, trust boundaries, or webhook security requirements. In an agent-skill context, this is risky because it normalizes outbound registration with an external service and could lead operators to expose internal endpoints or identifiable agent metadata without reviewing privacy, authentication, and SSRF-related implications.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrase "discover" is extremely broad and likely to match many unrelated user requests, causing the skill to activate outside its intended service-discovery context. Because this skill can initiate calls to external discovery and paid x402-backed endpoints, accidental invocation can lead to unintended network actions, noisy agent behavior, or unnecessary paid requests.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The phrase "new tools" is ambiguous and can match common conversational requests unrelated to this specific external service-discovery skill. In this skill's context, such overbroad matching is more dangerous because invocation may cause the agent to query a third-party service or progress toward subscription/payment flows without the user specifically asking for this provider.

VirusTotal

43/43 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.