Security audit

PostKing · Social

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent PostKing social media workflow guide, but users should confirm destructive or account-disconnect actions before execution.

Before installing, understand that this skill can publish or schedule public social posts, manage brand assets and templates, and disconnect social accounts through PostKing. Confirm account IDs, post times, and irreversible deletes before letting an agent act.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The skill instructs the agent to call `disconnect_social_account` directly and notes only that past posts are not deleted, but it does not require an explicit confirmation step or user warning before disconnecting an account. In an agentic workflow, a misunderstood request or prompt injection could cause unintended loss of publishing capability across a brand's social channels.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill describes `template_delete({ templateId, brandId? })` as irreversible but does not instruct the agent to obtain explicit confirmation before invoking it. Because templates are reusable content assets, accidental or induced deletion could cause permanent loss of organizational drafting resources.

Static analysis

No suspicious patterns detected.