ClawHub
Back to skill

Security audit

Launch Strategy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a launch-planning guide with no hidden code, install behavior, persistence, or sensitive data handling beyond reading an optional local marketing context file.

Before installing, note that the skill may activate for casual launch or announcement phrasing and may read a local product-marketing context file if your workspace has one. It does not appear to run commands, install software, persist changes, or access credentials.

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 invocation description includes broad conditions like 'when the user wants to plan a product launch' and especially 'use this whenever someone is preparing to release something publicly,' which lacks clear boundaries for when the skill should or should not activate. Although many listed phrases are domain-specific, the catch-all wording makes the trigger scope ambiguous and increases the risk of unintended invocation in ordinary product discussions.

Vague Triggers

Medium
Confidence
91% confidence
Finding
This JSON eval file contains natural-language requirements stating the skill 'Should trigger on casual phrasing' and asserts 'Triggers on casual phrasing.' That describes an activation expectation that is broad and ambiguous, increasing the risk of unintended invocation because it does not define clear boundaries or exclusions.

Static analysis

No suspicious patterns detected.