ClawHub
Back to skill

Security audit

Map

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only business strategy mapping skill with no code execution, external access, persistence, or privileged behavior.

Installers should understand this skill may be selected for some broad business-planning prompts, but its behavior is limited to structuring strategic advice and it does not request tools, credentials, file access, network access, or persistent changes.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrase at line 31 is broad enough to match ordinary planning language, which can cause the skill to activate outside the user's intended context. Overbroad activation increases the chance of prompt-routing mistakes, unintended invocation, and interference with other skills handling generic business or roadmap queries.

Vague Triggers

Low
Confidence
93% confidence
Finding
The manifest defines a trigger set composed of generic business-planning phrases without clear boundaries for when the skill should or should not activate. This can lead to ambiguous routing and accidental selection in common conversations, reducing reliability and potentially exposing users to unintended behavior from the wrong skill.

Static analysis

No suspicious patterns detected.