ClawHub
Back to skill

Security audit

Chinese Journal Paper

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese academic paper drafting skill whose repository reading is disclosed and purpose-aligned, with no evidence of hidden execution or data exfiltration.

Safe to install with normal caution. Use it only on repositories you are allowed to analyze, remove secrets or proprietary material you do not want included in model context, and manually verify generated claims, experiments, and references before submission.

SkillSpector

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 (3)

Vague Triggers

High
Confidence
98% confidence
Finding
The trigger set is overly broad and likely to activate on ordinary conversations about papers, journals, or writing, causing the agent to route users into this skill without clear intent. In context, this is dangerous because the skill performs repository scanning and generates substantial academic content, so misrouting can lead to unnecessary code access, privacy exposure, or unwanted academic-writing behavior.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill description hard-codes Chinese-language output and Chinese journal conventions without explicit user opt-in, which can override user preferences and cause inappropriate content generation. While not a severe security flaw, it is a real safety/control issue because it can mis-handle requests and steer outputs into a constrained format the user did not authorize.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding
The single-word trigger '论文' is so generic that it can match many unrelated or preliminary discussions, causing accidental invocation of a skill that scans code repositories and produces long-form academic content. In this skill's context, broad activation is more dangerous than usual because it may initiate analysis of project code based on a weak signal, increasing the chance of unintended data processing.

Static analysis

No suspicious patterns detected.