ClawHub
Back to skill

Security audit

agentself

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wrapper for a local agent identity CLI, but users should treat it carefully because it can involve secrets, email, and a live wallet.

Install this only if you intend to use agentself as a local identity tool and are comfortable letting an agent run agentself commands that may touch secrets, email setup, identity files, and wallet authorization. Check the CLI version and executable path first, avoid printing secret values, and review wallet actions manually because the documented default wallet can move real funds.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description is broad enough to activate for common requests involving email, wallets, secrets, identity initialization, or handoff. Because this skill can expose or manipulate sensitive local identity material and even access a live wallet, overly broad routing increases the chance of accidental invocation in contexts where a less-privileged skill should be used.

Static analysis

No suspicious patterns detected.