ClawHub
Back to skill

Security audit

Evolve

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local automation wrapper for changing active OpenClaw skills, but its safeguards and mutation boundaries are not documented enough for that level of control.

Review the local evolvectl.sh implementation before use, especially what paths it can modify, whether promote overwrites active skills, whether backups are created, and whether rollback has been tested. Use it only in a workspace where automated skill changes are acceptable.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises promotion and rollback commands that can alter active local skills, but it does not clearly warn users that these operations are state-changing and may modify or replace local configuration or code. In an autonomy/DevOps context, missing this warning increases the chance of unsafe invocation, accidental privilege misuse, or unintended disruption of the local skill environment.

Static analysis

No suspicious patterns detected.