Back to skill

Security audit

Umnix constitution for ai agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static governance guide with some high-impact example permissions, but it does not install code, request credentials, or act on data.

Before using this as policy guidance, clarify who can draft, approve, create, and amend constitutions in your organization. Do not include secrets or personal data in public constitutions, and treat financial, refund, database, and messaging examples as requiring explicit, scoped human-approved policies.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · skill.md (reported line 203)May include surrounding context.

Pattern 3: Customer-Facing Support Agent

yaml
Mandates:
  - MUST respond to all customer inquiries
  - MUST maintain professional tone
  
Permissions:

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 42)May include surrounding context.

md
- "MAY access customer database for support queries"
- "MAY send automated email responses"
- "MAY schedule meetings on behalf of users"
- "MAY process transactions up to $500 without approval"

**Characteristics:**
- Actions outside permissions are prohibited by default

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document presents conflicting statements about agent autonomy in constitutional governance: earlier it says agents can create their own constitutions, while later it says agents cannot unilaterally change their own governance and only organization admins can amend. In a governance skill, this ambiguity can cause unsafe implementations where agents are incorrectly granted self-governance or amendment authority, undermining oversight and dispute controls.

Content

No source excerpt is available for this finding.