ClawHub
Back to skill

Security audit

Crawdaddy

Security checks across malware telemetry and agentic risk

Overview

CrawDaddy is an instruction-only security scanning skill with no executable payload, but users should confirm data handling before submitting private code or secrets.

Install only if you are comfortable submitting the target repository, contract, or skill package to CrawDaddy and any integrations it uses. Do not submit private code, regulated data, or real credentials unless you have confirmed authorization, retention, provider, and monitoring terms.

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
This markdown file describes submitting a code repository URL and having CrawDaddy scan it, and later lists integrations with GitHub, GitLab, blockchain RPC endpoints, and AI agent platforms. However, it does not warn users about potential transmission of repository contents, metadata, or other sensitive security data to external systems, which is relevant to privacy and system-integrity expectations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.