ClawHub
Back to skill

Security audit

One Person Company

Security checks for vulnerabilities and agentic risk

Overview

This skill is a minimal connector-style description for an external AI assistant platform, with no bundled code or hidden execution behavior.

Install only if you are comfortable giving this external service an API key and allowing it to retain context for assistant workflows. Review the provider's documentation for what data is stored, how autonomous workflows are approved, and how memory can be deleted or limited.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description advertises multi-agent orchestration, autonomous workflows, task delegation, and persistent memory without warning users about data handling, retained context, or the possibility of actions being taken across systems. Because the skill is explicitly designed to automate and persist work, missing disclosure meaningfully raises the risk of users unknowingly exposing sensitive information or authorizing unintended operations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is broad and does not define clear activation boundaries or user-approved conditions for invoking a platform capable of orchestration and autonomous workflow execution. In an agent ecosystem, ambiguous scope can cause over-invocation or invocation in contexts the user did not intend, increasing the chance of unnecessary access to user tasks, data, or downstream actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.