ClawHub
Back to skill

Security audit

social-share-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for building social share buttons and does not ask for hidden access, persistence, or unsafe execution.

Installers should understand that this skill may activate for social sharing UI tasks and will guide agents toward using public platform share links or the browser's native share dialog. It does not introduce code execution or privileged access, but users should still review generated share URLs and icons for brand compliance and privacy expectations.

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

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says the skill should be used when the user wants to "add, optimize, or audit social share buttons," which is broader than the later specific phrase list and could match many general UI or marketing requests. The file does not provide exclusion examples or clearer constraints for when this skill should not activate beyond a brief distinction from profile links.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.