ClawHub
Back to skill

Security audit

self-improving-x (support multi-agent)

Security checks for vulnerabilities and agentic risk

Overview

This prompt-only skill is not malware, but it can automatically save conversation/error details and change future agent guidance without clear consent or redaction controls.

Install only if you want durable agent self-improvement notes in the workspace. Before using it, require explicit review before writing .learnings entries or changing AGENTS.md, CLAUDE.md, SOUL.md, TOOLS.md, copilot instructions, or .agents/skills, and add rules to redact secrets, tokens, customer data, internal URLs, sensitive paths, and full command output unless the user approves.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to automatically persist user corrections, requests, errors, and contextual details into local markdown files, but it does not require consent, minimization, redaction, or any warning that conversation content may be stored. This creates a real privacy and data-retention risk because sensitive prompts, credentials, proprietary details, or personal data could be written to disk and later exposed through local access, backups, version control, or subsequent agent reads.

Static analysis

No suspicious patterns detected.