ClawHub
Back to skill

Security audit

Cn LLM

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AIsa LLM client that sends user-provided prompts to the disclosed AIsa API, with no hidden persistence or unrelated behavior found.

Install only if you intend to use AIsa-hosted LLM routing. Treat prompts, system prompts, and message histories passed to the CLI as data sent to AIsa and potentially downstream model providers; avoid sending secrets or private conversation history unless that is acceptable for your use case.

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/cn_llm_client.py (reported line 250)May include surrounding context.

python
epilog="""
Examples:
    %(prog)s chat --model qwen-max --message "Hello!"
    %(prog)s chat --model deepseek-coder --message "Write a quicksort"
    %(prog)s chat --model deepseek-r1 --message "Which is larger, 9.9 or 9.11?"
    %(prog)s chat --model qwen-plus --message "Tell a story" --stream
    %(prog)s chat --model glm-4 --system "You are a poet" --message "Write a poem about spring"

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/cn_llm_client.py (reported line 251)May include surrounding context.

python
Examples:
    %(prog)s chat --model qwen-max --message "Hello!"
    %(prog)s chat --model deepseek-coder --message "Write a quicksort"
    %(prog)s chat --model deepseek-r1 --message "Which is larger, 9.9 or 9.11?"
    %(prog)s chat --model qwen-plus --message "Tell a story" --stream
    %(prog)s chat --model glm-4 --system "You are a poet" --message "Write a poem about spring"
    %(prog)s compare --models "qwen-max,deepseek-v3" --message "What is 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/cn_llm_client.py (reported line 253)May include surrounding context.

python
%(prog)s chat --model deepseek-coder --message "Write a quicksort"
    %(prog)s chat --model deepseek-r1 --message "Which is larger, 9.9 or 9.11?"
    %(prog)s chat --model qwen-plus --message "Tell a story" --stream
    %(prog)s chat --model glm-4 --system "You are a poet" --message "Write a poem about spring"
    %(prog)s compare --models "qwen-max,deepseek-v3" --message "What is AI?"
    %(prog)s models
        """

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

The chat command is explicitly designed to send arbitrary user messages, optional system prompts, and full JSON message arrays to a remote LLM provider. Because the interface accepts whole conversation payloads and does not validate, redact, or warn about sensitive content, it can leak secrets, internal instructions, or personal data to an external service.

Content

Scanner excerpt · scripts/cn_llm_client.py (reported line 262)May include surrounding context.

python
subparsers = parser.add_subparsers(dest="command", help="Commands")

    # Chat command
    chat_parser = subparsers.add_parser("chat", help="Send chat request")
    chat_parser.add_argument("--model", "-m", required=True, help="Model identifier")
    chat_parser.add_argument("--message", help="User message")
    chat_parser.add_argument("--messages", help="Full message array (JSON format)")

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares access to sensitive capabilities via environment variables and implied network use, but does not define any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap where a host agent may invoke the skill with broader capabilities than necessary, increasing the chance of unintended secret exposure or uncontrolled external API access.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description explicitly frames the skill around "Chinese LLM access," and the markdown repeats this Chinese-focused scope without stating that users may choose another language or that the restriction is region-specific. This can be a language/locale policy issue because the skill appears to impose a language-specific context without opt-in or a documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description says to use the skill whenever the user needs model configuration, provider guidance, or routing workflows, and the examples include broad phrases like "Help me configure AIsa for Qwen." These conditions are fairly open-ended and lack clear boundaries or exclusion cases, which could cause the skill to match general assistance requests rather than a narrowly defined invocation context.

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/cn_llm_client.py (reported line 31)May include surrounding context.

python
class CNLLMClient:
    """China LLM Unified Gateway Client."""

    BASE_URL = "https://api.aisa.one/v1"

    # Supported Chinese LLMs (from marketplace.aisa.one/pricing)
    SUPPORTED_MODELS = {

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The CLI takes user-supplied prompts and message history and forwards them to a third-party remote API, but the tool does not provide any explicit warning, consent prompt, or privacy notice at the point of transmission. In a skill context, users may assume local processing; this increases the risk of unintentionally sending sensitive prompts, system instructions, or conversation history to an external provider.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.