ClawHub
Back to skill

Security audit

KJ's Self-Improving Proactive Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local-memory and proactivity helper, with no evidence of hidden code execution, exfiltration, or unsafe automatic high-impact actions.

Install only if you want the agent to keep local cross-session notes about preferences, corrections, active work, and proactive patterns. Review the files under ~/self-improving/ and ~/proactivity/ periodically, and avoid putting secrets or highly sensitive context into those memory files.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly defines multiple persistent files for corrections, preferences, heartbeat state, and working context, but it does not prominently disclose to the user that this data will be written to disk and retained over time. That creates a privacy and consent risk: users may reveal sensitive preferences, project details, or operational context without understanding that the agent is designed to persist them locally across sessions.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- repeated 3x in 7 days → promote to HOT
- unused 30 days → demote to WARM
- unused 90 days → archive
- never delete confirmed preferences without asking

### Proactive patterns
- keep only moves that repeatedly create value
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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
This skill NEVER:
- infers durable rules from silence
- sends messages, spends money, deletes data, or makes commitments without approval
- stores credentials or secrets in memory files
- rewrites unrelated files without the user asking for integration
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.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs writing durable and session state into fixed paths under the user's home directory, including persistent learning and active working memory, but provides no user notice, consent flow, retention limit, or safety boundary around what may be stored. This creates a real privacy and integrity risk because an agent could silently persist sensitive task context, preferences, or project information across sessions and modify local files without the user's informed approval.

Static analysis

No suspicious patterns detected.