Back to skill

Security audit

Miaoji Bid Guard Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a local Amazon ads planning skill with heuristic recommendations and no evidence of hidden access, persistence, exfiltration, or automatic account changes.

Install only if you are comfortable using Chinese-language, heuristic Amazon advertising guidance. Treat ROI curves, budget shifts, and projected gains as planning prompts, not verified forecasts, and review recommendations before applying them in any ad platform.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The description markets a substantially broader and more advanced advertising planning product than the code actually provides. The code supports three concrete features: A/B test simulation, time-slot bidding suggestions, and budget allocation optimization, plus a basic bid calculator. However, it does not implement 90-day ROI prediction, seasonal bidding adjustments, or any keyword attack/defense matrix. While the budget optimizer touches multiple campaigns, that is narrower than the declared 'complete campaign planning' and 'multi-campaign coordination' framing. This is therefore a description-behavior mismatch due to missing headline capabilities and overstated primary purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file’s user-facing description and operational instructions are entirely in Chinese, and there is no statement that users may choose another language or that the skill is restricted to a Chinese-speaking or region-specific audience. Under the policy, mandating a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description and module header promise advanced capabilities such as 90-day ROI prediction, campaign coordination, seasonality, and keyword attack/defense analysis, but the implementation only provides simple heuristic bid calculation, static time-slot advice, and a basic budget redistribution routine. This is dangerous because users may rely on materially overstated functionality for advertising spend decisions, leading to financial loss or misplaced trust in outputs that appear more sophisticated than they are.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code hard-codes a specific locale assumption ('美国时区' and 'PST') while the rest of the skill presents itself in Chinese, and it does not provide any opt-in or alternative locale handling. The policy allows locale constraints only when clearly documented and justified or when the user is given a choice; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README content is fully presented in Chinese and does not offer an alternative language or indicate that the user can choose the locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The display name, description, and author fields are entirely in Chinese, and the manifest does not state that the skill is region-specific or offer an alternative language option. Under the policy, natural-language content that implicitly forces a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The function is presented as a budget optimizer, but it uses fixed heuristics, hard-coded improvement claims, and simple threshold-based redistribution rather than real optimization. This can mislead operators into believing the recommendations are evidence-based and expected gains are reliable, which may cause poor allocation of ad budgets.

Content

No source excerpt is available for this finding.