ClawHub
Back to skill

Security audit

Realtime Collab App

Security checks for vulnerabilities and agentic risk

Overview

This is a minimal instructional skill for building real-time collaboration apps, with no embedded executable code or persistence; its scope is broad but consistent with its stated purpose.

Installers should treat this as a lightweight starter prompt rather than a complete scaffold. Review or create any referenced helper scripts before running them, and be mindful that real-time collaboration apps may involve network services, Redis, shared document state, and user content once implemented.

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

Low
Confidence
93% confidence
Finding
The metadata description is overly broad and does not define clear boundaries, permitted actions, or invocation constraints for the skill. In an agent ecosystem, vague capability descriptions can cause overbroad routing or misuse, increasing the chance that the skill is invoked in contexts involving sensitive real-time data handling, collaborative editing, or networked interactions without adequate guardrails.

Static analysis

No suspicious patterns detected.