简历生成技能（W工作室）

Security checks across malware telemetry and agentic risk

Overview

This resume skill is useful, but it gives users a local-only privacy promise while later directing them to upload sensitive resume data to an external website.

Review before installing if you plan to enter real personal details. Use placeholder or minimized data unless you are comfortable uploading the generated resume JSON to aicv.weinuo.work, and delete local JSON, PDF, and markdown backup files when no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Intent-Code Divergence

Medium

Confidence: 96% confidence
Finding: The skill explicitly assures users that all resume content is processed locally and never uploaded, but later instructs them to import the generated resume into an external website. That contradiction can mislead users into disclosing highly sensitive personal data under a false privacy expectation, including full identity, contact details, employment history, and education records.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: This is a true privacy/security issue because the skill encourages users to provide sensitive PII while omitting a warning that the final workflow involves transferring that data to a third-party website. In context, the skill handles resumes, which are unusually sensitive and often contain enough information for phishing, identity profiling, and targeted social engineering.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal