ClawHub
Back to skill

Security audit

Edvisage Agent Connect

Security checks for vulnerabilities and agentic risk

Overview

This is a simple coordination-template skill with no executable code, but users should avoid placing secrets or sensitive personal data in shared handoff logs.

Use this skill for structured handoffs, but keep shared context files limited to task-relevant information. Do not include credentials, tokens, private customer data, or unnecessary personal details unless you have a clear reason and appropriate access controls.

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
89% confidence
Finding
The skill instructs agents to maintain a shared context file, task queue, and communication log, but provides no safeguards for minimizing, redacting, classifying, or obtaining approval before sharing sensitive data. In a multi-agent setting, this can lead to unnecessary propagation of personal, confidential, or security-relevant information across agents and logs, increasing exposure and retention risk.

Static analysis

No suspicious patterns detected.