ClawHub
Back to skill

Security audit

Social Content Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a plain writing-assistant skill for drafting social media content, with no code, persistence, credential use, or automatic posting behavior.

Before installing, understand that this skill may activate for general social media drafting requests and may lead the agent to research hashtags or posting times. It does not appear to post content, access accounts, install code, or persist settings on its own.

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
92% confidence
Finding

The activation description says the skill applies whenever a user wants to create social media content for any platform, which is a very broad condition. Although example trigger phrases are provided, the scope still lacks clear boundaries or exclusion conditions, increasing the risk of unintended invocation for ordinary content-help requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.