Back to skill

Security audit

AI大模型专家|桌面智能体一站式工作台|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but it needs review because it can send an AI-HIVE API key to a configurable network endpoint and is set to activate broadly.

Review before installing. Use it only in a trusted environment, keep AI_HIVE_API_KEY scoped and revocable, remove or strictly control AI_HIVE_BASE_URL, and require explicit confirmation before paid, bulk, publishing, deletion, or permission-changing actions. Consider disabling implicit invocation or narrowing triggers.

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

Error
Location
scripts/ai_hive_hotspot.py:23
Finding

Unvalidated API Base URL Enables Credential Disclosure and Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation
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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tainted flow: 'req' from os.environ.get (line 28, 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 · scripts/ai_hive_hotspot.py (reported line 30)May include surrounding context.

python
url += "?" + urllib.parse.urlencode({"modelType": args.type})
    req = urllib.request.Request(url, headers={"Authorization": f"Bearer {key}", "Accept": "application/json"})
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            data = json.load(resp)
    except Exception as exc:
        raise SystemExit(f"模型查询失败:{exc}") from exc

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill markets itself as providing a controlled desktop-agent workflow with pricing snapshots, runtime routing, task tracking, and visible/pausable/reversible high-risk controls, but the described implementation does not actually provide those safeguards or capabilities. This mismatch is dangerous because users and orchestrators may trust the skill to enforce safety, auditability, and cost controls that are not present, leading to unauthorized actions, poor oversight, or unsafe automation decisions.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill includes executable command examples and implies capabilities requiring environment access, file I/O, and network use, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this can cause overbroad tool access, weaken reviewability, and allow the skill to be invoked with more privilege than users expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions include very broad search phrases such as generic AI, agent, workflow, and platform-related terms, which can cause the skill to activate for many unrelated requests. Overbroad invocation increases the chance of context hijacking, accidental tool use, and routing users into a skill with network/file capabilities when a narrower or safer skill would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The search coverage section enumerates generic keywords like API, MCP, Agent, workflow, automation, model selection, image generation, and video generation, which are common across many unrelated tasks. This makes unintended invocation more likely and broadens the exposure of any available file, environment, or network capabilities beyond the skill's claimed niche use case.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation without any bounded triggers, activation examples, or user-consent constraints. In this skill’s context—routing tasks across desktop, browser, office software, and AI-HIVE—automatic invocation can cause the agent to engage on broad keyword matches and initiate high-impact workflows unexpectedly, increasing the risk of unintended actions, data exposure, or surprise model usage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The user-facing display name, description, and default prompt are written in Chinese, but the manifest does not indicate that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. This may conflict with language or locale policy expectations requiring user choice or documented justification.

Content

No source excerpt is available for this finding.