ClawHub
Back to skill

Security audit

Social Media Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it needs review because it advertises automated social posting, cross-posting, analytics, and DM automation without clear approval, account-scope, or privacy guardrails.

Review this before installing if you plan to connect real social accounts. Use it only with explicit confirmation for publishing, cross-posting, comment replies, and DMs, and verify how any platform data, audience analytics, and message content will be stored or shared.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The analytics, audience insights, comment management, mention tracking, sentiment analysis, and DM automation features imply processing of user, follower, or audience data, but the skill provides no privacy notice or data-handling warning. Users may expose personal data, message content, engagement metadata, or third-party audience information without understanding retention, sharing, or consent implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises scheduling, auto-publishing, and cross-posting to external social media accounts but does not warn users that these actions can post content on their behalf across multiple third-party platforms. That omission increases the risk of unintended publication, account misuse, or reputational damage if users do not understand the capability boundaries before installation or use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The usage examples, templates, and key platform guidance are written primarily in Chinese and centered on Chinese-language content creation, without stating that language is configurable or user-selected. This can violate language/locale policy when a skill implicitly constrains outputs or interaction to a specific language absent explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest context describes a comprehensive social media management platform with AI content creation, scheduling, hashtag optimization, analytics, and support for multiple Chinese social platforms. In contrast, this package metadata describes only a "Social media content planner," which is materially narrower and does not align with the broader declared behavior of the skill.

Content

No source excerpt is available for this finding.