Security audit

product-compare

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language product comparison helper with disclosed web research behavior and no bundled code or persistence.

Install this if you want a Chinese-language shopping comparison workflow. Expect it to search the web and review sources, and verify prices, seller claims, and user-review quality before acting on recommendations. Broad Chinese trigger phrases may cause it to activate on general recommendation requests.

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: This markdown file uses Chinese throughout for the description, workflow, and cautions, which effectively forces a specific language for users. The file does not indicate that the skill is China-specific or provide any user opt-in or alternative language, matching the language/locale policy violation criteria.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list includes very generic terms such as '对比', '推荐', and '哪个好', which are common in ordinary conversation and can cause the skill to activate outside the user's intended context. This creates an invocation-hijacking risk where unrelated shopping or recommendation requests may be routed to this skill, increasing the chance of misleading recommendations or unintended data handling.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The description and trigger phrases are entirely in Chinese, which implies the skill is designed to operate in a single language without any documented user choice or opt-in. There is no indication that this is a region-specific skill or that alternative language support is intentionally constrained and disclosed.

Static analysis

No suspicious patterns detected.