ClawHub
Back to skill

Security audit

iLearned Self Improving Agent

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because it found no AIG issues and judged the reported memory and gateway-restart findings expected for its purpose, though overall confidence is medium and Skillspector coverage is partial.

The verdict is benign, not a guarantee of safety. Consider whether persistent memory and the setup guide's gateway restart fit your needs. Skillspector inspected both listed components, but analysis was marked partial because two local path-like references were unresolved, so the evidence is incomplete.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied command restarts a gateway rather than storing, searching, or applying persistent lessons. Although it appears in a setup reference, the supplied content establishes no connection between this restart and ilearned memory functionality, so it constitutes an undeclared operational capability.

Content

No source excerpt is available for this finding.

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
---
name: ilearned-self-improving-agent
description: >
  Use ilearned as persistent rule-book memory. Activate on user corrections,
  tool/command failures, knowledge gaps, recurring mistakes, or verified better
  approaches; also search before tasks where past lessons are likely to help
  (planning, research, tool use, communication). Prefer structured when/if/do/check