ClawHub
Back to skill

Security audit

Cve Alerts

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a CVE monitoring workflow with expected local configuration, scheduled scans, and optional alerts, with no hidden code or deceptive behavior found.

Before installing, treat the config and data directories as sensitive because they may reveal watched technologies, suppressions, alert history, and possibly alert credentials. Prefer environment variables or a secrets manager for SMTP or Telegram secrets, and use restrictive permissions such as private user-only config and data directories.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs operators to configure persistent local storage and optional alerting credentials (SMTP/Telegram) but does not warn that these files may contain sensitive secrets and monitoring data. This can lead users to store credentials in plaintext or in broadly readable locations, increasing the risk of credential leakage or unauthorized access to security alerting infrastructure.

Session Persistence

Medium
Category
Rogue Agent
Content
## Quick Start

1. Create config directory and watchlist:
```bash
mkdir -p ~/.config/cve-alerts
```
Confidence
73% confidence
Finding
The skill directs users to create persistent configuration under ~/.config/cve-alerts and later references a local data directory for seen items, suppressions, and config, which introduces session/state persistence on disk. In this context the persistence itself is expected for a monitoring tool, but without guidance on permissions, retention, and secret handling it can expose watchlists, suppression rules, and alerting credentials to other local users or backups.

Static analysis

No suspicious patterns detected.