ClawHub
Back to skill

Security audit

add.tools

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only tool-search helper that sends searches and optional feedback to add.tools, with no local code, persistence, or privilege use evident.

Install only if you are comfortable sending search terms and optional feedback to add.tools. Do not include secrets, private project names, credentials, or confidential prompts in searches or feedback, and review any returned tool or paid endpoint before allowing an agent to use it.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The feedback example encourages sending user queries, chosen tools, and success outcomes to a remote service without any warning about privacy, consent, or data minimization. In an agent setting, this can lead to inadvertent exfiltration of sensitive prompts, internal tool selections, or user behavior metadata to a third party.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# JSON response for agents
curl -H "Accept: application/json" "https://add.tools/search?q=send+email"

# With explicit format param
curl "https://add.tools/search?q=weather+forecast&format=json"
Confidence
85% confidence
Finding
curl -H "Accept: application/json" "https://add.tools/search?q=send+email" # With explicit format param curl "https://add.tools/search?q=weather+forecast&format=json" ``` ### Report feedback ```bas

VirusTotal

43/43 vendors flagged this skill as clean.

View on VirusTotal