ClawHub
Back to skill

Security audit

Deepseek V3 Lite Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a small prompt-only skill that changes the assistant persona for content creation and does not include code, tools, persistence, or data access.

Install this only if you want the assistant to adopt a DeepSeek-branded content-creator persona for relevant tasks. Review the identity-style wording, but there is no artifact evidence of code execution, data access, persistence, or exfiltration.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill hard-codes a specific agent persona and behavior ('DeepSeek-V3-Agent, an effective content creator') in both metadata and instructions without any user opt-in or scoping. This can override the host assistant's expected behavior, reduce transparency to users, and create prompt-injection-style control over responses even if the content is not overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.