ClawHub
Back to skill

Security audit

event-driven-coordinator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only coordination skill with broad routing language, but it does not contain code, install hooks, hidden behavior, credential handling, or persistence.

Installers should treat this as an architecture guidance skill. It may be invoked for fairly broad coordination discussions, so users should keep sensitive deployment decisions and production actions under explicit human review, but no artifact-backed malicious or high-risk automatic behavior was found.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill description is broad enough to attract invocation for many loosely related coordination, architecture, and workflow tasks without clearly bounding what the skill should and should not do. In an agent-routing context, ambiguous descriptions can cause mis-selection, over-privileged use, or unintended delegation paths, increasing the chance that unsafe instructions or sensitive context are sent to the wrong skill.

Static analysis

No suspicious patterns detected.