Back to skill

Security audit

Chinese Journal Paper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese academic-paper drafting helper that reads project code to summarize technical contributions, with no executable payload, persistence, or hidden data transfer found.

Install only if you want an agent to analyze project files for Chinese journal-paper drafting. Review generated claims, experiments, and citations manually; do not treat the skill's citation-verification table as evidence that references were actually checked unless the agent shows sources.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (10)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: chinese-journal-paper
description: "从项目代码仓库出发,自动扫描代码提取创新点,撰写符合中文核心/普刊规范的学术论文。核心能力:① 代码仓库扫描与技术创新点提炼 ② 参考文献格式占位(用户手动填充) ③ 生成完整论文(标题、摘要、关键词、引言、相关工作、方法、实验、结论)。触发词:论文、写论文、期刊论文、学术论文、核心期刊、普刊、中文论文、journal paper、帮我写论文、从代码写论文、项目写论文。当用户提到'论文'且上下文涉及代码或项目时,应�

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger set is broad enough to activate on common requests about 'papers' or writing, even when the user did not ask for repository scanning or Chinese journal formatting. Over-broad routing can cause unintended invocation, unnecessary codebase analysis, and generation of domain-specific academic output that does not match user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description defaults to Chinese core/general journal output without clear user opt-in. While not directly code-execution dangerous, this can override user preferences, produce unintended locale-specific content, and steer the agent into a specialized workflow the user did not request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest lists many triggers but lacks scope constraints, exclusions, or disambiguation guidance. That makes accidental or inappropriate activation more likely, which is risky because this skill encourages repository scanning and structured long-form generation based on potentially sensitive project contents.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill states that it will not automatically search for or fabricate references, but later claims references are '尽量验证' and requires a verification log. This inconsistency can mislead downstream agents or users into believing citations were checked when they were not, increasing the risk of fabricated scholarship, false provenance, and unsafe automation around academic claims.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file presents all instructions and templates exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience. Under the language/locale policy, 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

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is entirely framed as a mandatory guide for Chinese journal academic writing style, beginning with the title and continuing throughout the document. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
89% confidence
Finding

A single-word trigger like '论文' is too generic and can match many benign conversations. In the context of a skill that may scan repositories and produce specialized academic output, this creates an avoidable risk of misrouting and over-collection of project information.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

The trigger '普刊' is short, ambiguous, and likely to appear in unrelated discussion about publication types. This increases accidental activation and may push users into an unintended workflow that analyzes code or drafts a full paper without adequate confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The text states that GB/T 7714 is the standard format and proceeds as a prescriptive guide in Chinese, without indicating that this format applies only when the user specifically needs Chinese academic citation rules. This can be a locale-specific policy issue because it implicitly forces a China-specific citation standard rather than offering a choice or clarifying the intended regional context.

Content

No source excerpt is available for this finding.