Back to skill

Security audit

Newton Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Newton-perspective reasoning skill with disclosed research-style web lookup behavior and no evidence of hidden code, persistence, credential access, or destructive actions.

Install this if you want a Chinese-language Newton-style reasoning persona. Be aware it may route broad scientific-method or first-principles prompts into this persona and may perform web research for fact-based questions.

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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes broad terms like “科学方法”, “归纳推理”, and “第一性原理”, which can match many ordinary reasoning requests unrelated to this persona. That overbroad activation can cause unintended routing of user prompts into a roleplay skill that also instructs mandatory tool use, increasing the chance of unnecessary web access, scope confusion, and degraded safety/policy handling.

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 is written entirely in Chinese from the title onward, with no indication that the user can choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill mandates a fixed persona and expression style without offering user choice, which can override user-preferred language or format and reduce transparency about the model’s normal behavior. In context this is mainly a quality and controllability issue, but it can also make outputs less aligned with user intent and harder to audit when the persona injects procedural requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the skill or document is intentionally region-specific or that users may choose another language. Per the policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing natural language content entirely in Chinese, including the title and all section text, but does not indicate that Chinese is required or provide any user opt-in or alternative language option. Under the language/locale policy check, forcing a single language without user choice can be a policy violation when no justification is given.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is natural-language content, and it consistently presents the material only in Chinese. Under the language/locale policy check, forcing a single language without opt-in can be a policy violation when no alternative or user choice is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file is written entirely in Chinese and labels the researcher as "Agent5-决策," which suggests a language-specific output format. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue when no choice or justification is provided.

Content

No source excerpt is available for this finding.