Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Security audit
光通信投资分析框架（中文版）
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly a coherent Chinese-language investment-analysis knowledge base, but its optional updater asks to use a logged-in browser profile and also suggests periodic checks, which needs user review before install.
Install only if you are comfortable with a Chinese-language, stock-analysis skill that may update its own reference notes. For the update workflow, prefer manually supplied article text or an isolated browser profile instead of your normal logged-in Chrome session, and avoid any scheduled checks unless you explicitly configure and supervise them.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (20)
Vague Triggers
Medium
- Confidence
- 93% confidence
- Finding
- The trigger list includes broad, common domain terms such as '光通信', '光模块', and 'OCS', which can cause the skill to activate during ordinary discussion rather than intentional invocation. In this skill, unintended activation matters because the same skill also contains instructions for external browsing and persistent knowledge modification.
Missing User Warnings
Medium
- Confidence
- 95% confidence
- Finding
- The skill instructs use of a logged-in Chrome profile ('profile="user"') to repeatedly access Xueqiu, but does not adequately address the security implications of reusing an authenticated browser session. This creates risk of unintended access to account-scoped data, session abuse, or cross-site actions if browsing behavior expands or the page content is adversarial.
Intent-Code Divergence
Medium
- Confidence
- 96% confidence
- Finding
- The skill claims self-iteration only runs with explicit user triggering, but later recommends periodic scheduled checks. That contradiction weakens operator expectations and can lead to autonomous browsing and content ingestion without fresh consent, especially when using a logged-in browser profile.
Vague Triggers
Medium
- Confidence
- 97% confidence
- Finding
- The document presents user-explicit triggering as a safety boundary, then undermines it with scheduled activation guidance. This increases the risk that the agent will perform recurring checks, browse external sites, and alter local reference files outside the narrow context the user expected.
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- This markdown file is entirely written in Chinese and presents the skill content in a single enforced language without any indication of user opt-in, fallback, or alternative locale. The policy for natural-language violations applies to all file types and specifically flags language or locale constraints that are imposed without user choice.
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Natural-Language Policy Violations
Medium
- Confidence
- 84% confidence
- Finding
- This markdown file is written entirely in Chinese and presents the framework as the default form without any note that other languages are available. Under the policy, forcing a specific language without user opt-in can be a natural-language locale violation when no alternative or opt-in is documented.
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
- Suspicious Unicode normalization or mixed-script content
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- This markdown file is entirely presented in Chinese, starting with a Chinese-only title and continuing throughout without offering an alternative language or indicating that the skill is region-specific. Under the 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
- 90% confidence
- Finding
- This markdown file is entirely presented in Chinese from the title onward, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. The policy requires flagging language or locale constraints when they are imposed without opt-in or clear justification.
Natural-Language Policy Violations
Low
- Confidence
- 83% confidence
- Finding
- This markdown file consists entirely of Chinese-language content and does not indicate that the user can choose another language or that the locale restriction is intentional. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Natural-Language Policy Violations
Low
- Confidence
- 88% confidence
- Finding
- SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all user-facing content in Chinese only, with no opt-in, alternative language, or justification that the skill is intended solely for a Chinese-language or region-specific audience.
Natural-Language Policy Violations
Low
- Confidence
- 95% confidence
- Finding
- This markdown file contains user-facing natural-language content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the language/locale policy, forcing a single language without opt-in can be a policy concern.
Natural-Language Policy Violations
Low
- Confidence
- 84% confidence
- Finding
- This markdown file presents all skill content in Chinese and does not indicate that users may select another language or locale. Under the policy check for natural-language constraints, forcing a single language without user opt-in can be considered a locale/language policy violation.
Natural-Language Policy Violations
Low
- Confidence
- 89% confidence
- Finding
- SQP-3 applies to all file types and includes language or locale policy violations. This markdown file presents all headings and substantive guidance in Chinese only, and nowhere indicates that the user can choose another language or that the Chinese-only scope is an explicit, justified regional constraint.
Natural-Language Policy Violations
Low
- Confidence
- 90% confidence
- Finding
- This markdown file is entirely written in Chinese, beginning with the heading '更新日志', and does not indicate that the language choice is optional or tied to a documented region-specific purpose. Under the policy rule for language or locale constraints, this can be considered a natural-language policy violation because it implicitly fixes the skill content to a specific language without opt-in.
Static analysis
No suspicious patterns detected.