ClawHub

deep-java-review

Security checks across malware telemetry and agentic risk

Overview

This is a Java code review helper whose repository inspection and report-writing behavior match its stated purpose, but users should invoke it deliberately because it can read project code and create Markdown files.

Install only if you want an agent to inspect Java project changes and generate review artifacts. Before running it, specify the repository, branch or diff range, and whether reports should be written to files or returned only in chat; review generated Markdown before committing it.

SkillSpector

By NVIDIA
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

Medium
Confidence
92% confidence
Finding
The trigger phrases are extremely broad and overlap with normal developer requests such as code review, bug checking, performance analysis, business analysis, and PRD generation. This can cause the skill to activate unintentionally in unrelated contexts, leading the agent to run repository inspection and file-writing behavior the user may not have explicitly requested.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The 'when to use' section defines invocation conditions in broad, non-specific terms like '用户需要进行代码评审' and common phrases such as '检查bug' or '业务分析'. These vague boundaries increase the chance of over-triggering the skill for ordinary conversation, which is risky because the skill directs use of git, bash, and workspace writes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to write `code-review-report.md` and `prd-{版本号}.md` into the workspace, but the description and activation guidance do not clearly warn users that files will be created or modified. In combination with broad triggers, this can produce unexpected workspace changes, overwrite existing files, or leak analyzed content into tracked project files without informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal