Security audit
Security checks for vulnerabilities and agentic risk
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.
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.
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.
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.
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.
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.
- 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
---
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.
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.
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.
No suspicious patterns detected.