ClawHub
Back to skill

Security audit

Llm Eval Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for evaluating local Ollama models against cloud providers, with expected API use and local score storage.

Before installing, confirm you are comfortable sending task prompts and candidate outputs to the named LLM providers for evaluation, storing score history locally, and running a scheduled accumulator if you implement that optional production loop.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (1)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- **Per-task weight overrides**: do not use one weight profile for all task types.
  Structural accuracy (difflib) is wrong for prose analysis — use semantic similarity as
  the primary signal for open-ended tasks. This lifted analyze mean from 0.44–0.59 to 0.70.
- **Structured output prompts for analyze tasks**: add a `system_prompt` that specifies
  an exact output format (Finding/Recommendation/Confidence/Reasoning). Both GT and
  candidates follow the same template, improving structural alignment and reducing drift
  penalty. Without this, Layer 2 drift fires on differently-phrased but correct analyses.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.