Back to skill

Security audit

除秽·调优魄

Security checks for vulnerabilities and agentic risk

Overview

This is a localized performance-tuning skill whose cleanup and optimization guidance is disclosed and purpose-aligned, but users should confirm before allowing state-changing actions.

Install only if you want a Chinese-language performance optimization helper. Treat its cleanup and tuning suggestions as potentially state-changing: ask for diagnostics first, review proposed commands, require confirmation before deletion or configuration changes, and keep backups for anything important.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly includes cleanup and tuning actions, including 'executing cleanup operations,' but does not clearly warn that these may change system state, remove data, affect running services, or degrade functionality if misapplied. Because the skill is framed as environment optimization, users may interpret the actions as inherently safe, increasing the chance of destructive or user-impacting modifications without informed consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are broad enough to activate on common requests like 'system is slow' or 'clean up the environment,' which can cause the skill to take or propose system-altering actions without clear scoping, confirmation, or safety boundaries. In the context of a performance and cleanup skill, this raises the risk of unintended execution of impactful changes such as deleting files, altering configs, or tuning services based on ambiguous user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill's natural-language description and usage instructions are presented in Chinese throughout, with no indication that the user can choose another language. This can violate a language/locale policy when a skill implicitly forces one language without opt-in or justification.

Content

No source excerpt is available for this finding.