Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Security audit
物理解题教学指导
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed Chinese junior-high physics teaching skill with bounded class-record handling and no hidden executable, network, or persistence mechanism.
This skill is appropriate for Chinese-language junior-high physics teaching contexts. Before installing outside that setting, localize the language, curriculum assumptions, privacy rules for minors, and crisis-support channels. Teachers should keep student records pseudonymous and use the consent and deletion controls described in the skill.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)
Vague Triggers
Medium
- Confidence
- 89% confidence
- Finding
- The trigger phrases are broad enough to match ordinary teaching requests such as generic 'how to teach this physics problem' or 'students are weak at physics problem solving.' In an agent-routing environment, this can cause over-triggering, pulling the conversation into this skill when a more appropriate skill should handle lesson planning, assessment, experiments, or general pedagogy, leading to context leakage and unintended data sharing across dependent skills.
Natural-Language Policy Violations
Medium
- Confidence
- 80% confidence
- Finding
- The file is explicitly scoped to ‘初中’ learners, but the motion-analysis section lists “匀加速/匀减速/曲线” and vector-style decomposition like “水平 + 竖直” and “径向 + 切向”, which goes beyond the stated junior-high framing and may impose an unstated instructional policy/locale mismatch. This is especially notable because the document elsewhere says certain higher-level content should not be required.
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Natural-Language Policy Violations
Medium
- Confidence
- 97% confidence
- Finding
- The entire skill file is written in Chinese and presents the instructional content as the default output format, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The entire template and instructional content are written in Chinese, with no indication that users may choose another language or that the locale restriction is required for a region-specific compliance purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file is entirely written as a Chinese-only instructional skill and does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the regional constraint is explicitly documented and justified.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The entire skill file is written in Chinese and includes instructional content and user-facing phrasing only in Chinese, with no indication that other languages are supported or that the user has opted into Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Natural-Language Policy Violations
Medium
- Confidence
- 92% confidence
- Finding
- The document states that the library is designed for Mainland China Chinese K12 scenarios, with simplified Chinese wording and Mainland China help channels as defaults. This is a natural-language locale policy constraint, and the file does not present it as a user-selectable option or opt-in within the skill behavior.
Natural-Language Policy Violations
Low
- Confidence
- 91% confidence
- Finding
- SQP-3 applies to all file types and covers natural-language policy issues such as forcing a specific language without user opt-in. This markdown file presents all instructions and content solely in Chinese, with no indication that the skill is region-specific or that users can choose another language.
Static analysis
No suspicious patterns detected.