Back to skill

Security audit

跨学科侦探周

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese K12 study skill that stores cross-subject project notes only through stated profile handoff controls.

Install this only if a Chinese K12 study workflow and persistent student learning records are appropriate. Before using it outside mainland China, localize crisis contacts, curriculum assumptions, and minor-consent rules; ensure the student or guardian understands the profile writeback and cross-skill sharing controls.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description is entirely written as if the skill is to be invoked and used in Chinese, including all trigger phrases, with no indication that other languages are supported or that Chinese is an opt-in choice. This creates a natural-language policy concern because it imposes a specific language/locale on users without user selection or documented justification.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and policy-like guidance exclusively in Chinese, including operational requirements for skills. The review criteria require flagging language or locale policy violations when a skill forces a specific language without user opt-in, and this file does not offer alternatives or justify a China-specific language constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The text states that the repository is designed for '中国大陆的中文 K12 场景' and fixes curriculum alignment, language, and default safety resources to mainland China. This is a natural-language locale policy constraint that applies by default rather than offering the user a language or regional choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest/schema contains user-facing natural-language descriptions entirely in Chinese, including the main note and description fields. Because the file does not state that the skill is China/Chinese-specific or offer a language choice, it may violate the language/locale policy requiring opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.