Security audit

Local Model Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed routing guide for using local Ollama models and cloud fallback, with no bundled code, persistence, or hidden high-impact behavior.

Install only if you intend the agent to route some prompts through local Ollama models and to use DeepSeek cloud for fallback cases. Review the model names and routing rules for your own privacy expectations, especially if prompts may contain sensitive data.

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 (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The model assignment table explicitly prefers a model for 'Hızlı, doğal Türkçe', indicating a language-specific behavior. The file does not mention any user choice, fallback, or opt-in for other languages, which is a natural-language locale policy concern.
Content: No source excerpt is available for this finding.

External Transmission