Simplified Social Media

• Outcome: Review
• Latest audit: Sep 11, 2026 · 3:01 PM UTC
• Version: 1.2.2

Overview

The skill is a coherent social media integration, but it can publish or queue real public posts through a remote service without a clear final confirmation step.

Install only if you trust Simplified with the connected social media accounts and are comfortable giving this MCP server posting authority. Before using it, require your agent to show the exact accounts, message, media, action, and scheduled time, then get explicit approval before any queue, schedule, or direct publish action.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The trigger list contains broad phrases such as "social media," "post to," and "publish on," which can match routine user requests and cause the skill to activate in contexts the user did not intend. Because this skill can ultimately publish or schedule content to external accounts, accidental activation increases the risk of unintended high-impact actions.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: Generic analytics triggers like "analytics," "reach analytics," "impressions," and "social insights" are likely to match ordinary discussion or requests unrelated to this specific integration. This broad matching can expose connected account metadata or analytics unnecessarily and route users into an external MCP workflow they did not ask to use.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill instructs the agent to proceed through a publish workflow against external social media accounts without requiring an explicit user confirmation immediately before creating a post. In this context, accidental or misinterpreted requests can lead to real-world state changes on public-facing accounts, including queued or scheduled content that may damage brand reputation.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill explicitly promotes autonomous campaign execution and end-to-end posting workflows without any review or approval checkpoint. In a tool that can broadcast content across multiple platforms, this materially increases the chance of mass unintended publication, especially if the agent mis-parses instructions or is prompted by untrusted content.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

- If the user mentions a timezone or location (e.g. "Warsaw", "New York", "CET"), pass it as `tz` using IANA format (e.g. `Europe/Warsaw`, `America/New_York`)
- If the user's timezone is known from context, always pass `tz` explicitly
- If timezone is unknown and the data is time-sensitive (daily breakdown), ask the user before proceeding
- For simple totals or aggregated KPIs, UTC is acceptable without asking

---

• Confidence: 75% confidence
• Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The guide explicitly defines Instagram `direct` as immediate publishing but does not warn that selecting this option can post content live to a connected account. In a social-media automation skill, missing this safety cue increases the risk of unintended publication, especially if an agent or user assumes actions are only drafts or reminders.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The TikTok section documents `direct` as immediate publishing without a clear warning that content may go live on the user's real account. Because this skill is specifically designed to automate posting across many platforms, the omission can contribute to accidental public posting, brand damage, or disclosure of unreviewed content.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The Threads `direct` option is described as publishing immediately, but the guide provides no explicit caution that this affects a live connected account. In the context of a cross-platform posting tool, that missing warning materially increases the chance of unintended or premature publication across customer-facing channels.

Static analysis

No suspicious patterns detected.