Back to skill

Security audit

光通信投资分析框架

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed investment-analysis knowledge base, but its optional updater can use a logged-in browser profile and has ambiguous scheduled-check wording.

Install only if you want a Chinese-language optical-communications investing reference skill. Do not allow the update workflow to run on a schedule; trigger it manually, review any browser use of your Xueqiu login session, and inspect appended reference changes before relying on future analyses.

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 (14)

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad domain terms such as '光通信', '光模块', and 'CPO', which are likely to appear in ordinary conversation. That makes accidental activation plausible, including unintended entry into workflows that may later request browser use, file edits, or knowledge-base modification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that self-iteration only runs on explicit user request, but later recommends periodic scheduled checks. This contradiction can lead an agent to perform external browsing and content ingestion without a fresh user action, expanding the skill from static analysis into semi-autonomous data collection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file creates inconsistent activation rules by saying self-iteration requires explicit user triggering while elsewhere allowing scheduled checks. Ambiguous trigger policy is dangerous because an agent may interpret passive timing guidance as authorization to browse external sites or modify references without the user clearly requesting it.

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.

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
90% confidence
Finding

This markdown file is written entirely in Chinese and the title establishes the skill/document in a single language without any indication that users may choose another language or locale. Under the policy criteria, forcing a specific language without user opt-in is a natural-language locale violation unless it is clearly documented as region-specific or optional.

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.

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.

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.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The scheduled-check instruction is vague and lacks any clear opt-in, scope limit, or confirmation requirement. In a skill that can browse logged-in content and append to local reference files, even a loosely worded recurring check increases the risk of unintended external access and silent state changes.

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 content exclusively in Chinese, and there is no indication that the skill is region-specific or that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

This markdown file is entirely in Chinese, and there is no indication that the skill supports other languages or that the Chinese-only presentation is an intentional, justified regional limitation. Under the policy rule, forcing a specific language without user 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
82% confidence
Finding

The document begins with a Chinese-only heading and the entire file content is written in Chinese, with no indication that language choice is optional or that the skill is intentionally region-specific. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.