ClawHub
Back to skill

Security audit

Local Inference Context

Security checks for vulnerabilities and agentic risk

Overview

This skill gives operational guidance for managing local LLM context pressure and does not show hidden code execution, exfiltration, or disproportionate authority.

Install this if you use local llama.cpp or Ollama backends and want conservative context-management behavior. Be aware it may store operational checkpoints and local backend status in memory, and it may query localhost services during troubleshooting.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

--format=csv,noheader,nounits

Check llama.cpp slot state

curl -s http://localhost:8081/slots | python3 -m json.tool

text

If `memory.free` is less than 4 GB, treat the session as already amber

Static analysis

No suspicious patterns detected.