ClawHub
Back to skill

Security audit

Alazab Global Context

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed production operations context, but it attaches globally to every agent/session and allows some automatic production actions, so it needs careful review before installation.

Install only if you intend this Alazab-specific production policy to influence all matching agents and sessions. Review the wildcard auto-attach behavior, production endpoints/paths, shell executor assumptions, and automatic approval rule, and consider narrowing scope before using it outside the intended environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

High
Confidence
94% confidence
Finding
This context is configured with auto_attach=true and wildcard applicability across all agents, models, runtimes, sessions, projects, and nodes, which creates a system-wide implicit trust boundary. In a production orchestration environment, that means any prompt, policy, path, or operational instruction in this file is injected everywhere by default, amplifying the blast radius of mistakes or malicious edits and increasing the chance of unintended privilege or behavior propagation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
},
    "execution": {
      "default_approval_policy": "gated",
      "non_destructive_auto_approve": true,
      "destructive_requires_owner": true,
      "forbidden_without_explicit_approval": [
        "DROP DATABASE",
Confidence
83% confidence
Finding
auto_approve

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.install_untrusted_source

Install source points to URL shortener or raw IP.

Warn
Code
suspicious.install_untrusted_source
Location
alazab-portal-ai-global-context.json:81