ClawHub
Back to skill

Security audit

Business Automation Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a business automation planning guide with templates and safety practices, not code that executes actions or accesses data by itself.

Installers should treat this as a planning framework. For any automation involving money, customer communications, legal/compliance, HR, security, credentials, or production data, keep explicit human approval, sandbox testing, rollback, logging, and least-privilege access in place.

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
90% confidence
Finding

The quick-start phrases are generic operational requests such as auditing processes or recommending a platform, which could be triggered by normal user conversation rather than an explicitly scoped skill invocation. In an agent environment that auto-loads or prioritizes skills based on natural-language matching, this can cause unintended activation and influence the agent's behavior without clear user intent.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
10. Backup and archival

**Automate LAST** (complex, high risk):
1. Anything involving money transfers without approval
2. Customer-facing responses without review
3. Legal/compliance decisions
4. Hiring/firing workflows

Static analysis

No suspicious patterns detected.