Back to skill

Security audit

ClawFetch.ai Web Intelligence API

Security checks for vulnerabilities and agentic risk

Overview

The web-data service fits its description, but its setup prints the wallet’s private key before asking you to fund that wallet.

Review the wallet setup before use. Remove private-key logging and use protected key storage; replace any wallet whose key has already appeared in logs before funding it. Use a dedicated wallet with a small balance and a spending limit. Treat submitted URLs, queries, and documents as information shared with ClawFetch.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Wallet creation could support a payment workflow, but this chunk only generates and prints wallet credentials, including the private key. That standalone behavior is materially different from the declared web intelligence service and does not demonstrate an X402 payment implementation. No network transmission or external exfiltration is shown.

Content

No source excerpt is available for this finding.

Wallet setup prints the private key without warning about exposure through logs or agent transcripts.

High
Category
Output Handling
Confidence
99% confidence
Finding

The setup explicitly prints wallet.privateKey, potentially exposing it through captured stdout, agent transcripts, monitoring, or shared logs. Anyone obtaining that key can control the wallet and steal funds subsequently deposited into it; the instruction to save the key securely does not prevent the initial disclosure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md
});

// Now use it like normal fetch — payments happen automatically!
const response = await x402Fetch('https://api.clawfetch.ai/render', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ url: 'https://example.com' }),

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md
});

// Now use it like normal fetch — payments happen automatically!
const response = await x402Fetch('https://api.clawfetch.ai/render', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ url: 'https://example.com' }),

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

bash
# 1. Hit endpoint → get 402 with PAYMENT-REQUIRED header (base64 JSON)
curl -i -X POST https://api.clawfetch.ai/fetch \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

bash
# 1. Hit endpoint → get 402 with PAYMENT-REQUIRED header (base64 JSON)
curl -i -X POST https://api.clawfetch.ai/fetch \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
# 4. Base64-encode the signed payload
# 5. Resend with PAYMENT-SIGNATURE header

curl -X POST https://api.clawfetch.ai/fetch \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <base64-encoded-signed-payload>" \
  -d '{"url": "https://example.com"}'

The workflow sends URLs and research queries to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

These instructions direct the agent to route web-fetching and research tasks through ClawFetch, transmitting target URLs and research queries to an external service. The skill does not warn that these inputs may reveal confidential topics or sensitive URL parameters, or instruct the agent to exclude sensitive data.

Content

No source excerpt is available for this finding.