ClawHub
Back to skill

Security audit

Agent Communication

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown protocol for agent-to-agent communication with disclosed delegation behavior and no executable code, installer, persistence, or hidden data handling.

Install only if you want agents to communicate or delegate tasks to other agents. When using it, avoid forwarding unnecessary private context, and confirm long-running background delegation when the task could affect important data or decisions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is very broad ('standardized cross-Agent communication protocol; use when you need to ask, collaborate with, or delegate to another Agent'), which can cause over-activation in many unrelated situations. Because this skill authorizes inter-agent messaging and task delegation, ambiguous triggering increases the chance of unnecessary data sharing, unintended delegation, or use of messaging controls in contexts where they were not needed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata and content are written in Chinese and implicitly prescribe that protocol text be emitted in that language, without stating that output should follow the user's preferred language. This can lead to user confusion, misrouting of requests, or incorrect operational use when agents or users expect another language, especially in cross-agent coordination where precision matters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.