ClawHub
Back to skill

Security audit

Team Communication

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple team-agent messaging guide with no executable code, persistence, credential handling, or hidden behavior found.

Install only if your team uses these session keys and expects Chinese-language guidance. Treat sessions_send messages as shared task context, and do not include secrets or private data unless explicitly appropriate.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is broad enough to trigger on many ordinary collaboration requests, which can cause the agent to invoke this skill in situations where communication with other agents is unnecessary or inappropriate. In a multi-agent environment, overly broad routing increases the chance of unintended message passing, unnecessary disclosure of task context, or workflow manipulation through excessive delegation.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill description and all user-facing guidance are written in Chinese and examples assume Chinese communication, but there is no opt-in or note that the skill is intentionally region- or language-specific. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation.

Static analysis

No suspicious patterns detected.