Back to skill

Security audit

Afrexai Regulatory Compliance.Skip

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only compliance checklist skill with broad compliance claims, but no hidden code, persistence, credential use, or unsafe install behavior.

Use this as a preliminary compliance checklist and planning aid only. Do not treat its output as legal advice, audit certification, or proof of compliance, and avoid providing unnecessary PHI, PCI, employee, customer, or confidential business data. Validate framework applicability, risk ratings, remediation plans, and budgets with qualified legal, security, privacy, or audit professionals before acting on them.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation phrase instructs the agent to 'run a regulatory compliance audit' for an arbitrary company description without defining scope boundaries, prohibited actions, data-handling limits, or required user confirmations. In an agent setting, this can cause over-collection of sensitive business, legal, or regulated data and may prompt the model to make unsupported compliance determinations across multiple frameworks, increasing the risk of unsafe or misleading outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill presents itself as able to run a full regulatory compliance audit for any business across multiple jurisdictions and frameworks, but it does not warn users that the output is not legal advice and must be validated by qualified legal, privacy, security, or compliance professionals. This creates a material risk that users will rely on incomplete or inaccurate AI-generated compliance determinations, leading to regulatory gaps, improper filings, missed obligations, or unsafe business decisions.

Content

No source excerpt is available for this finding.