ClawHub
Back to skill

Security audit

Local web search using SearXNG

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent SearXNG web-search skill whose main risk is exposing search queries to the configured search server, especially if HTTP is used.

Install only with a SearXNG instance you trust. Prefer HTTPS for non-local endpoints, avoid putting secrets or sensitive personal data in search queries, and be aware that broad prompts may trigger external search if the agent follows this skill's trigger guidance.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
searxng_search.py:55
Finding

Search Queries Can Be Transmitted over Plaintext HTTP and Exposed in URLs

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tainted flow: 'req' from os.environ.get (line 62, 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 · searxng_search.py (reported line 68)May include surrounding context.

python
})

    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            data = json.loads(resp.read().decode())
    except urllib.error.HTTPError as e:
        return {"error": f"HTTP {e.code}: {e.reason}", "query": query}

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill performs network access and depends on environment variables, but it does not declare an explicit tool scope such as permissions or allowed-tools. This creates ambiguity for the agent/runtime about what capabilities are intended, which can lead to overbroad execution or accidental access beyond what users or operators expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad, including common phrases like 'look up', 'what is', and 'google', which are likely to match many ordinary prompts. This can cause unintended invocation of a network-enabled skill, leading to privacy leakage of user prompts or unnecessary external requests when the user did not explicitly ask for web search.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.