ClawHub
Back to skill

Security audit

AI Code Review

Security checks across malware telemetry and agentic risk

Overview

This code-review skill is legitimate in purpose, but it can direct an agent to use GitHub access to change, commit, and push code without a clear approval step.

Install only if you want a code-review workflow that may inspect PRs and CI through your GitHub login. Before using it, tell the agent that edits, commits, pushes, dependency fixes, or audit fixes require explicit approval of a specific diff.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s activation examples are broad, generic phrases like 'レビューして', 'コードをチェック', and '品質を確認', which can overlap with ordinary conversation and unrelated requests. This increases the chance of unintended invocation, causing the agent to run repository-inspection commands or review workflows in contexts where the user did not explicitly consent to using this skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
reference.md:418