Back to skill

Security audit

Miaoji Bid Guard

Security checks for vulnerabilities and agentic risk

Overview

This skill provides Amazon advertising bid and budget advice without hidden automation, credential use, persistence, or platform access.

Installers should treat this as an advisory calculator and planning aid, not as a live Amazon Ads automation tool. Verify all ACoS benchmarks and financial assumptions against current account data, and manually review any bid, budget, or pause recommendation before applying it in an ad account.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

声明与代码部分匹配:代码确实围绕亚马逊广告出价护栏、ACoS上限、利润边界、预算模拟和出价建议展开。但声明中有多项重要能力未在代码中体现,尤其是“生成视频广告脚本”和“熔断策略/熔断建议”,代码完全没有任何内容生成或自动暂停/熔断逻辑。代码也没有真正按关键词实体进行分析,而是用整体平均CPC、转化率等聚合参数生成通用规则;因此“分析广告关键词出价”只算部分贴近。另,“秒级出价方案生成”更像实时系统能力,而该代码只是一次性CLI计算脚本。综合看,主用途接近,但声明显著夸大了实际能力,因此应判定为描述与行为存在不匹配。

Content

No source excerpt is available for this finding.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/bid-calculator.py (reported line 136)May include surrounding context.

python
"message": f"Top of Search premium: bid up to ${round(max_cpc * 1.3, 2)} only for keywords with >8% conv rate",
    })

    return rules


def analyze(params: dict) -> dict:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description, headings, examples, and interaction pattern are entirely in Chinese, and the sample user/AI exchange implies the skill operates in Chinese by default. There is no statement that users may choose another language or that the Chinese-only scope is a justified regional constraint, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description states the skill should be used whenever a user needs several loosely related tasks, including bid guardrails, circuit-breaker strategy, and video ad script generation, without defining clear activation boundaries or exclusions. Overly broad activation can cause the agent to trigger in inappropriate contexts, increasing the chance of unintended data handling, irrelevant automation, or unsafe business recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese, beginning with the title at L001 and continuing throughout the document. Under the language/locale policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The user-facing report strings are hard-coded in Chinese, while the script description, usage, and CLI help are in English. This creates a language policy issue because the skill does not offer a language choice or explain that it is intended only for a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest emphasizes ACoS limits, keyword bid analysis, guardrail generation, circuit-breaker advice, and video ad script creation. This function implements multi-level budget simulation and profit projection, which is a broader financial planning capability not clearly justified by the stated purpose of a bid-guardrail advisor.

Content

No source excerpt is available for this finding.