ClawHub
Back to skill

Security audit

Diffbot Fetch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Diffbot article-extraction helper, with expected network use and API-token handling for its stated purpose.

Install only if you are comfortable sending requested article URLs and the Diffbot API token to Diffbot. Avoid using it on private, internal, authenticated, or sensitive links unless that sharing is intended and allowed by your policies.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tainted flow: 'req' from os.environ.get (line 27, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · fetch.py (reported line 31)May include surrounding context.

python
# Add a standard user agent just in case
        req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64)")
        
        with urllib.request.urlopen(req) as response:
            data = json.loads(response.read().decode('utf-8'))
            
            if "error" in data:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly promotes fetching arbitrary URLs through the Diffbot Article API but does not disclose that the target URL and retrieved page content are sent to a third-party service. This can mislead users into processing sensitive, internal, or private links under the assumption the tool operates locally, creating confidentiality and compliance risks.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill declares use of an environment variable and makes outbound network requests, but does not define any explicit tool scope such as permissions or allowed-tools. This weakens sandboxing and reviewability because an agent may invoke code with broader capabilities than the skill contract clearly communicates, increasing the chance of unintended secret access or arbitrary external requests.

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 · fetch.py (reported line 18)May include surrounding context.

python
sys.exit(1)

    # Prepare the API request URL
    base_url = "https://api.diffbot.com/v3/article"
    params = {
        "token": api_key,
        "url": url

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill transmits both the user-provided URL and the Diffbot API token to a third-party service without any explicit user-facing notice or consent mechanism. In this skill's context, outbound transmission is core functionality, but it can still expose sensitive internal URLs, private document links, or browsing targets to an external processor if users are unaware of the data flow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.