ClawHub
Back to skill

Security audit

Multi-model automatic fallback system

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent model-fallback configuration guide, but users should know fallback can send requests to alternate model providers.

Install only if you are comfortable with failed or routed requests being sent to the configured backup model providers. Disable or tightly configure fallback for sensitive prompts, regulated data, or workloads restricted to a single provider.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill automatically routes prompts to alternate providers such as MiniMax, Kimi, and Zhipu, but the description does not clearly warn users that their inputs may be transmitted to different third-party services during fallback. This creates a real data-governance and privacy risk because users may submit sensitive prompts assuming a single provider, while fallback silently broadens disclosure to additional external parties with different retention, jurisdiction, or policy characteristics.

Static analysis

No suspicious patterns detected.