ClawHub
Back to skill

Security audit

Cross Agent Chat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple cross-agent messaging guide with disclosed behavior and no executable code, though users should avoid sending sensitive information to other sessions.

Install only if you want agents to communicate with other sessions. Before sending, confirm the target session is authorized and remove secrets, credentials, personal data, internal prompts, or unrelated user content from the message.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs operators to send messages to other sessions but never warns that those messages may contain sensitive user, system, or operational data that will be disclosed outside the current session boundary. In a cross-agent communication skill, that omission materially increases the risk of unintended data exfiltration, especially because the workflow encourages discovering sessions and forwarding task context to them.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill documentation is entirely in Chinese and all examples assume Chinese-language interaction, but there is no indication that this is a region-specific skill or that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.