ClawHub
Back to skill

Security audit

Agent Core

Security checks for vulnerabilities and agentic risk

Overview

The published skill is only a Markdown promotional listing with external purchase links, so it does not itself install or run the advertised automation.

Installing this published artifact should not by itself change your agent or run automation. Treat the linked paid kit or bundle as unreviewed external material: inspect its files before use, require explicit opt-in for email/calendar/trading/deployment access, and avoid enabling cron or persistent memory until storage, retention, and kill-switch behavior are clear.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description promises a broad 'AI agent operating system' that can be dropped into any agent and emphasizes persistent memory, heartbeat automation, and autonomous behavior, but it does not define clear activation boundaries, preconditions, or limits on when these behaviors should run. In an agent ecosystem, vague scope increases the chance the skill is invoked in inappropriate contexts and enables over-privileged or unexpected autonomous actions without informed user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises autonomous monitoring of emails, calendars, RAM, project status, weather, and scheduled reports, yet provides no user-facing disclosure about what data is accessed, how long it is retained, what side effects occur, or what system load and privacy risks follow from cron-driven execution. Because the context is specifically an agent framework designed for 24/7 operation with persistent memory, the omission is more dangerous: users may enable continuous collection, retention, and actioning over sensitive personal or operational data without meaningful notice or control.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.