ClawHub

Huo15 Openclaw Code Review

Security checks across malware telemetry and agentic risk

Overview

This is a coherent code-review helper, but it defaults to running nested review with full filesystem and approval bypass authority, so users should review that behavior before installing.

Install only if you are comfortable with an agent running this review helper in your repositories. Consider using the documented --no-yolo or AUTOREVIEW_YOLO=0 option, and avoid fallback reviewers when diffs may contain private code or secrets.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill advertises highly generic trigger phrases like "code review" and similar broad review requests, which can cause the skill to activate in conversations where the user did not explicitly intend to invoke this specific PR-review workflow. Because the skill can prompt for sensitive repository metadata and diffs, overbroad activation increases the risk of unintended data exposure or the wrong skill handling a request.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The alias list includes generic phrases such as "代码评审", "code review", and "review PR" without contextual constraints, making accidental or ambiguous invocation likely. In an agent ecosystem, such broad aliases can hijack routine discussion, route requests to an unintended skill, and cause unnecessary collection or display of code review data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal