ClawHub
Back to skill

Security audit

LLM Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AIsa LLM gateway client that sends user-chosen prompts and image URLs to AIsa when explicitly invoked.

Install only if you intend to use AIsa as an external LLM gateway. Do not send secrets, private documents, or sensitive image URLs through this skill unless your AIsa account and downstream provider policies are acceptable for that data.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (9)

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · scripts/llm_router_client.py (reported line 255)May include surrounding context.

python
formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
    %(prog)s chat --model gpt-4.1 --message "Hello!"
    %(prog)s chat --model claude-3-sonnet --message "Write a poem" --stream
    %(prog)s chat --model gpt-4 --system "You are a pirate" --message "Greet me"
    %(prog)s vision --model gpt-4o --image "https://example.com/img.jpg" --prompt "Describe this"

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · scripts/llm_router_client.py (reported line 256)May include surrounding context.

python
epilog="""
Examples:
    %(prog)s chat --model gpt-4.1 --message "Hello!"
    %(prog)s chat --model claude-3-sonnet --message "Write a poem" --stream
    %(prog)s chat --model gpt-4 --system "You are a pirate" --message "Greet me"
    %(prog)s vision --model gpt-4o --image "https://example.com/img.jpg" --prompt "Describe this"
    %(prog)s compare --models "gpt-4.1,claude-3-sonnet" --message "Explain AI"

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · scripts/llm_router_client.py (reported line 257)May include surrounding context.

python
Examples:
    %(prog)s chat --model gpt-4.1 --message "Hello!"
    %(prog)s chat --model claude-3-sonnet --message "Write a poem" --stream
    %(prog)s chat --model gpt-4 --system "You are a pirate" --message "Greet me"
    %(prog)s vision --model gpt-4o --image "https://example.com/img.jpg" --prompt "Describe this"
    %(prog)s compare --models "gpt-4.1,claude-3-sonnet" --message "Explain AI"
    %(prog)s models

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · scripts/llm_router_client.py (reported line 258)May include surrounding context.

python
%(prog)s chat --model gpt-4.1 --message "Hello!"
    %(prog)s chat --model claude-3-sonnet --message "Write a poem" --stream
    %(prog)s chat --model gpt-4 --system "You are a pirate" --message "Greet me"
    %(prog)s vision --model gpt-4o --image "https://example.com/img.jpg" --prompt "Describe this"
    %(prog)s compare --models "gpt-4.1,claude-3-sonnet" --message "Explain AI"
    %(prog)s models
        """

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README uses very broad activation language such as 'use when the user needs model configuration, provider guidance, or routing workflows,' which can cause the skill to be invoked in loosely related situations without clear boundaries. In a model-routing skill, overbroad invocation increases the chance of unnecessary exposure to provider setup steps, external service guidance, or downstream operational actions the user did not explicitly request.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill declares required environment access and is intended to perform model routing/provider setup, which implies network-capable behavior, but it does not declare an explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity where a user-invocable skill may access secrets like AISA_API_KEY and perform outbound actions without a clearly constrained execution contract, increasing the risk of overbroad capability use or accidental data exfiltration.

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 · scripts/llm_router_client.py (reported line 26)May include surrounding context.

python
class LLMRouterClient:
    """Unified LLM Gateway Client for AIsa API."""
    
    BASE_URL = "https://api.aisa.one/v1"
    
    # Popular models for reference (check marketplace.aisa.one/pricing for full list)
    SUPPORTED_MODELS = {

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The CLI sends user-provided prompts, system messages, and image URLs to a third-party API service, but it does not present an explicit user-facing notice or consent boundary at the point of use. In a skill context, this can cause accidental disclosure of sensitive data because users may reasonably assume the tool is operating locally unless warned otherwise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README advertises 'Chinese LLM access' as part of the skill's usage without indicating that this capability should only be used when the user explicitly opts in. That can steer routing toward a locale- or region-specific capability unnecessarily, which may create privacy, compliance, or expectation-mismatch issues depending on the provider and user context.

Content

No source excerpt is available for this finding.