Back to skill

Security audit

Afrexai Automation Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only business automation strategy skill that provides templates and planning guidance, with no executable code or hidden runtime behavior found.

Installers should treat this as planning guidance, not an automation executor. Review any generated workflow before implementing it, especially for payments, customer communications, HR, legal, compliance, security-sensitive tasks, or integrations involving credentials and private business data.

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
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
87% confidence
Finding

The README presents invocation phrases like "Audit my processes for automation opportunities" and "Assess our automation maturity" without any scope limits, exclusion conditions, or negative examples. These are natural-language requests that could overlap with ordinary business-assistance prompts, making activation boundaries unclear.

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