ClawHub
Back to skill

Security audit

Browser Use Api

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Browser Use cloud API helper, but users should understand that task prompts and resulting browser activity are sent to an external service.

Install only if you intend to use Browser Use's cloud service and have a Browser Use API key. Do not send credentials, private pages, regulated data, or sensitive form inputs through it unless you are comfortable with that provider processing the task, page interactions, and screenshots.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documents shell execution via curl commands and a helper script, but does not declare corresponding permissions or execution capabilities. This can mislead reviewers and users about what the skill is able to do, weakening security review and allowing command execution paths to be introduced without explicit scrutiny.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases include broad terms like "scrape website" and "automate web task," which can cause the skill to activate in situations where the user did not specifically intend to send work to this cloud service. Because activation may lead to external data transmission and browser automation, accidental invocation increases privacy and misuse risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill describes cloud browser automation and mentions screenshots in results, but it does not clearly warn users that their task contents, visited pages, form inputs, and screenshots are sent to a third-party cloud browser service. In this context, that omission is significant because users may provide sensitive URLs, credentials, or private data without understanding the external exposure.

External Transmission

Medium
Category
Data Exfiltration
Content
fi

# Submit task
RESPONSE=$(curl -s -X POST "$API_URL/tasks" \
  -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"task\": $(echo "$TASK" | python3 -c 'import json,sys; print(json.dumps(sys.stdin.read().strip()))')}")
Confidence
95% confidence
Finding
curl -s -X POST "$API_URL/tasks" \ -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \ -H "Content-Type: application/json" \ -d

External Script Fetching

High
Category
Supply Chain
Content
fi

# Submit task
RESPONSE=$(curl -s -X POST "$API_URL/tasks" \
  -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"task\": $(echo "$TASK" | python3 -c 'import json,sys; print(json.dumps(sys.stdin.read().strip()))')}")
Confidence
90% confidence
Finding
curl -s -X POST "$API_URL/tasks" \ -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \ -H "Content-Type: application/json" \ -d "{\"task\": $(echo "$TASK" | python

External Script Fetching

High
Category
Supply Chain
Content
# Poll for completion
ELAPSED=0
while [[ $ELAPSED -lt $MAX_WAIT ]]; do
  RESULT=$(curl -s "$API_URL/tasks/$TASK_ID" \
    -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY")
  
  STATUS=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin).get('status',''))" 2>/dev/null || echo "")
Confidence
90% confidence
Finding
curl -s "$API_URL/tasks/$TASK_ID" \ -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY") STATUS=$(echo "$RESULT" | python

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.