ClawHub
Back to skill

Security audit

ClawOps

Security checks for vulnerabilities and agentic risk

Overview

This skill openly describes managing all installed skills and secrets, but it does not define clear boundaries or user controls for that broad access.

Install only if you are comfortable with a skill acting as a central coordinator for other skills. Before using it with real workflows, require explicit configuration for which skills it may control, what triggers it may run, how secrets are stored or referenced, and whether logs redact sensitive data.

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
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly advertises centralized secrets management plus logging, monitoring, and orchestration across installed skills, but provides no user warning about the sensitivity and reach of those capabilities. In an orchestration skill, this omission is security-relevant because users may grant broad trust without understanding that secrets and activity from multiple skills could be aggregated, exposed in logs, or mishandled by dependent components.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.