Back to skill

Security audit

Esports commentator · Crayfish (Claw Claw)

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only game patch briefing skill with minor routing and language-scope caveats, but no hidden execution, data access, persistence, or destructive behavior.

Installers should expect Chinese-language game patch summaries and should invoke it with a clear game name and patch reference. The main caveat is possible over-activation from broad trigger terms, not unsafe system access.

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
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The metadata hard-codes language: zh-CN without indicating user preference, opt-in, or fallback behavior. In multi-language environments this can cause unwanted language forcing, miscommunication, and reduced user control, especially if the skill is auto-invoked for users who did not request Chinese output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list contains very broad terms such as "meta" and generic update-related phrases that can match ordinary conversation with limited game-specific context. This can cause the skill to activate unexpectedly, leading to inappropriate routing, user confusion, or the application of this skill in contexts where its assumptions do not fit.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.