Back to skill

Security audit

生成精美科研风格 HTML 文档,深度解析论文与对应代码实现。

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language report generator that reads user-provided paper and code paths and writes an HTML analysis report, with no evidence of hidden or unsafe behavior.

Install this if you want Chinese-language HTML reports for papers and code. Be aware it will need to read the paper and source code paths you provide and write an HTML file to the chosen location; avoid pointing it at private code or sensitive papers unless you are comfortable with those contents being summarized into the report.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is explicitly described and structured around Chinese-language output without offering any user language selection or fallback behavior. This can cause the agent to ignore user language preferences, produce unusable output for non-Chinese users, and create prompt-quality failures that may mislead users about the generated report's accessibility and correctness.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The typography section mandates Chinese-specific fonts, which hard-codes a Chinese locale assumption into the generated HTML. While less severe than the overall language constraint, it can degrade rendering, readability, and internationalization support when the report is generated for other languages or environments lacking those fonts.

Content

No source excerpt is available for this finding.