Security audit

ym-review-triage-reply

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese review-response drafting skill with clear limits and no account access, code execution, network use, auto-posting, or persistence.

Install this if you want a Chinese-language helper for drafting responses to negative reviews. Do not rely on it to verify orders, approve refunds, handle legal threats, or publish replies; review any draft against your store policy and compensation authority before sending.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrase "客户投诉" is ambiguous because it covers a much wider set of complaint-handling scenarios than store-review reply drafting, including refunds, legal threats, billing disputes, and support escalations. Overbroad activation can misroute sensitive or high-risk complaints into a template-reply skill that is not designed to safely handle them.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrase "客户投诉" is ambiguous because it covers a much wider set of complaint-handling scenarios than store-review reply drafting, including refunds, legal threats, billing disputes, and support escalations. Overbroad activation can misroute sensitive or high-risk complaints into a template-reply skill that is not designed to safely handle them.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The entire template is written as a mandatory Chinese response format, and line 3 states that every review reply must follow this file's structure. There is no indication that the skill is region-specific or that users may opt into another language, which creates a natural-language locale policy concern under the language/locale rule.

Vague Triggers

Low

Confidence: 84% confidence
Finding: The trigger list repeats broad phrases but does not define exclusion conditions or disambiguation rules, so the invocation boundary remains unclear. While not directly enabling code execution or data exfiltration, this increases the chance of accidental activation and inappropriate handling of user requests outside the skill’s narrow purpose.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: This markdown file contains user-facing guidance exclusively in Chinese, starting from the title and throughout the document. Under the policy rule for natural-language constraints, forcing a specific language without opt-in can be a locale/language policy issue when no justification or alternative is provided.

Static analysis

No suspicious patterns detected.