Back to skill

Security audit

复习规划师

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps Chinese K12 teachers plan review schedules and only saves plans after explicit teacher confirmation.

Install this for Chinese-language, mainland China K12 teacher workflows. Before use in another country, language, curriculum, or legal environment, localize the crisis referral numbers, grade and curriculum assumptions, and data-consent rules. Teachers should review saved review plans because the skill intentionally reads class learning data and writes persistent review schedules only after confirmation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description, display fields, and user-facing trigger examples are presented only in Chinese, which effectively forces a specific language/locale for activation and use. Under the policy, language constraints should either be user-selectable or explicitly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description states the workspace contract using Chinese-only terminology, and many downstream enums and field descriptions are defined exclusively in Chinese, implying the skill expects a fixed language/locale. Under the policy, forcing a specific language without user opt-in or a clearly documented locale-specific justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire shared instruction file is written as normative guidance in Chinese and contains prescriptive response wording such as asking and explaining to students in Chinese. There is no indication that users may choose another language or that the locale restriction is limited to a justified region-specific deployment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The text declares this file as the single source of truth for all terminology and requires all related documentation and schemas to reference its definitions, which are entirely in Chinese. This enforces a specific language/locale at the organizational level without any opt-in, alternative locale, or stated region-specific justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown file includes guidance for when skills are deployed to other languages or regions, but it does not define narrow trigger phrases or clear negative examples for when this localization policy should apply. Under the vague-trigger rule for markdown files, broad applicability language can cause inconsistent or unintended use across skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.