DeepSeep Intergration

Security checks across malware telemetry and agentic risk

Overview

This is a small placeholder DeepSeek tool that only echoes prompts and does not currently perform network, file, shell, persistence, or credential-access behavior.

This appears safe to install as a placeholder, but it is not a functional DeepSeek integration yet. If a future version adds real API calls, treat prompts, code, and related context as data that may be sent to DeepSeek, and avoid using it with secrets or sensitive material unless that is acceptable for your workflow.

SkillSpector

By NVIDIA

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 (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: This markdown file describes integration with the DeepSeek API and agent use for chat completions, code generation, and analysis, but it does not warn users that their prompts or related data may be sent to an external network service. For markdown files, omissions about behaviors affecting privacy or data handling should be flagged when the skill description does not disclose them.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal