ClawHub
Back to skill

Security audit

smartclaws-master-agent

Security checks for vulnerabilities and agentic risk

Overview

This skill can control configured SmartClaws devices and leave blockchain records, but those actions are openly described and scoped by owner configuration.

Install only if you intend this agent to operate configured SmartClaws devices. Review SMARTCLAWS.md and AGENTS.md carefully, especially which devices are commandable, who may trigger actions, and whether every run should create an on-chain decision log.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad enough to match ordinary user requests like checking devices, making decisions, commanding a device, or auditing decisions, which can cause the skill to activate in situations where the user did not clearly intend to run a control cycle. In this skill’s context, activation can lead to external device commands and on-chain writes, so ambiguous invocation boundaries increase the risk of unintended real-world actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill performs actions that can change device state and create irreversible on-chain records, but it does not prominently warn at invocation boundaries that using the skill may have external side effects and blockchain cost/finality implications. Because the procedure includes device commands, notifications, and decision-log publishing, a user may request a seemingly routine check and unintentionally trigger writes with persistent consequences.

Content

No source excerpt is available for this finding.