Security audit

fore-vip-geo-optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a marketing-content workflow, but it can install and run an external paid/payment skill and push drafts to WeChat without enough explicit user control.

Install only if you are comfortable with a marketing skill that performs web research and may interact with publishing accounts through other skills. Before use, require confirmation before any link fetch, browser/login-state action, WeChat draft push, SkillHub CLI installation, fore-vip-auto installation/update, or WeChat Pay/refund flow; avoid providing confidential or access-controlled URLs unless you intend them to be fetched.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly supports pushing content to WeChat official account drafts, but it does not clearly warn users that generated content may be transmitted to an external platform and may create account-side effects such as draft creation or publication preparation. In a skill that produces marketing content and chains into other skills, this omission increases the risk of unintended external actions under a user's authenticated account.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The skill invites users to provide materials or links that the system will fetch and extract online, but it does not warn that those URLs, linked content, and possibly embedded sensitive business information may be retrieved and processed externally. This can lead to accidental disclosure of confidential campaign plans, unpublished materials, or private documents if users paste sensitive links.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: This markdown file contains natural-language guidance only in Chinese, and there is no indication that the skill is limited to Chinese-speaking users or that language selection is optional. Per the policy, forcing a specific language without user opt-in can be a locale-policy violation.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The template explicitly tells the agent to fetch and auto-fill data from user-provided links, but it does not require any disclosure that external network access will occur or that linked content may be retrieved and processed. This can create privacy and trust issues, especially if users provide internal, tracking, or sensitive URLs expecting them to be treated as plain references rather than fetched content.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: This markdown file contains prescriptive natural-language guidance only in Chinese, including platform-specific style rules and compliance checks, without indicating that users may choose another language or locale. Under the policy rule for language/locale, forcing a specific language without user opt-in can be a policy violation.

Static analysis

No suspicious patterns detected.