ClawHub
Back to skill

Security audit

ClawHub Demo Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a minimal demo skill that only confirms it is active and optionally echoes user text, with no code execution, file creation, or external access.

This appears safe for basic smoke testing. Be aware that implicit invocation is enabled, so the skill could activate without an explicit $skill mention in some contexts; its current instructions are low risk, but future versions should keep that scope narrow or disable implicit invocation.

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
  • 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without any visible trigger constraints, which can allow the agent to call this skill in broader contexts than intended. While this demo skill appears low-risk because it only returns a confirmation and echoes a phrase, the setting still weakens invocation boundaries and could cause unintended activation or data flow if the skill behavior expands later.

Content

No source excerpt is available for this finding.