Back to skill

Security audit

Miaoji Compliance Copy

Security checks for vulnerabilities and agentic risk

Overview

This skill provides advisory Amazon listing copy checks and rewrites without hidden data access, account changes, credential use, or persistence.

Installers should treat the Amazon policy and Rufus scoring guidance as advisory and verify important listing changes before publishing, especially because the tool does not itself prove current Amazon compliance. No credential or account-modifying behavior was found.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The tagline and description require Chinese comprehension, but the manifest does not state that the skill is Chinese-only or provide any language/locale opt-in. Under the policy, forcing a specific language without user choice or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring says the tool scans listing text for prohibited words, over-marketing language, and policy violations, then generates replacement suggestions and a compliance score. However, the implementation also performs additional keyword-coverage analysis via generate_rufus_keywords and folds that into an overall_score, which is a materially different optimization capability than compliance checking.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The formatted user-facing report strings are all written in Chinese, regardless of the selected input language or any user preference. This creates a natural-language locale policy issue because the skill does not offer a report-language choice or document a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This markdown file presents all guidance in Chinese without offering an alternative language or indicating that the skill is intentionally region-specific, which can violate a policy requiring user language choice or opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

analyze does more than just invoke the two analyses: it truncates the title, packages category metadata, computes a weighted overall_score, and adds a timestamp. This is not a strong security issue by itself, but the documentation does not accurately describe the produced result object.

Content

No source excerpt is available for this finding.