ClawHub
Back to skill

Security audit

Self-Improving Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workspace learning logger with guarded memory promotion, and I found no hidden code, exfiltration, or automatic privileged behavior.

Install this only in workspaces where you want the agent to keep persistent learning notes. Review any proposed promotion into AGENTS.md, MEMORY.md, or similar instruction files before accepting it, because those files can influence future agent behavior.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
## Core rules

- Prefer **signal over volume**.
- Default to **logging**, not self-modifying instructions.
- Log only meaningful corrections, failures, recurring issues, durable conventions, or explicit “remember this” requests.
- Never log secrets, tokens, private keys, environment variables, raw customer data, or full sensitive transcripts unless the user explicitly asks.
- Prefer short summaries and redacted excerpts over raw output.

Static analysis

No suspicious patterns detected.