ClawHub
Back to skill

Security audit

Capability Awareness System

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only capability discovery guide and does not include code, hidden execution, credential access, or persistence beyond user-directed installation.

This appears safe to install as a documentation-oriented skill. Users should understand that its purpose is to make agents more aware of other installed skills, so future additions to the skill directory or prompt workflow should be reviewed because those external skills may carry their own risks.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SECURITY.md (reported line 61)May include surrounding context.

md
### What the Agent Cannot Do
- Access files outside workspace (OpenClaw sandbox enforces this)
- Execute arbitrary code (must use permitted OpenClaw tools)
- Bypass existing security controls
- Escalate privileges

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SECURITY.md (reported line 63)May include surrounding context.

md
- Access files outside workspace (OpenClaw sandbox enforces this)
- Execute arbitrary code (must use permitted OpenClaw tools)
- Bypass existing security controls
- Escalate privileges

### Permission Inheritance
- Skills operate within agent's existing permissions