ClawHub
Back to skill

Security audit

AANA Agent Memory Gate Skill

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is a user-consent guardrail for agent memory use and does not add code execution, persistence, or hidden data access.

Installers should understand that this skill changes agent behavior around memory decisions: it may cause the agent to ask before using or changing memories, especially sensitive ones. That behavior is disclosed and aligned with the package purpose.

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
  • 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 (1)

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 16)May include surrounding context.

md
- facts the user explicitly asked to remember,
- preferences the user clearly approved for future use,
- temporary task context that should not become memory,
- inferred traits that should not be stored without confirmation,
- sensitive information that should not be stored unless strictly necessary and explicitly approved,
- obsolete or incorrect memory that should be corrected or deleted with approval.

Static analysis

No suspicious patterns detected.