Back to skill

Security audit

专家人格锻造炉

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent expert-skill generator, but it defaults to writing a new skill into the user's skills directory without clear confirmation or overwrite safeguards.

Review before installing because this skill may cause an agent to create a persistent new skill file in your skills directory by default. Use it only when you want that local change, and ask the agent to preview the SKILL.md, confirm the destination path, and avoid overwriting existing files unless you explicitly approve.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is primarily written in Chinese and presents trigger phrases and usage guidance centered on Chinese-language interaction, without stating that language is optional or user-selectable. Under the policy rule, forcing a specific language or locale without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill directs the agent to write a complete SKILL.md into the user's skills directory by default, but it does not require explicit confirmation before modifying local files. In environments where Write/Edit are available, this can lead to unexpected filesystem changes, accidental overwrites, or persistence of prompt content the user did not clearly approve.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file is entirely framed in Chinese and presents the guidance as the default style for the skill-pattern library, with no indication that users may choose another language or locale. Under the policy for natural-language constraints, forcing a specific language without user opt-in is a reportable locale-policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.