ClawHub
Back to skill

Security audit

Albion Evolver

Security checks for vulnerabilities and agentic risk

Overview

This skill openly aims to modify and commit workspace code, but its autonomous write and rollback workflow is too broad without a clear user approval boundary.

Review this carefully before installing. Use it only in a disposable or clearly selected repository, expect it to read and modify workspace files, run git/python3, create commits, and keep an improvement log. Do not use it around private logs or credentials unless you are comfortable with its network-backed review workflow and have your own approval controls in place.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description presents autonomous self-improvement, code changes, sandbox execution, and git versioning as normal behavior without prominently warning users that it can modify code and create commits. Because the skill has shell and network permissions plus broad workspace write access, omission of this warning undermines informed consent and increases the chance a user invokes a powerful self-modifying workflow without understanding the consequences.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is explicitly designed to autonomously analyze logs, modify workspace code, run validation steps, and apply changes with git commits, but it does not define a clear user-approved trigger boundary for when this behavior may start. In a skill with shell, network, and workspace read/write permissions, vague activation language materially increases the risk of unintended or overly broad self-modification, especially if invoked in the wrong context or on the wrong repository.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.