Dataify Facebook Profile By URL

• Outcome: Pass
• Latest audit: Jul 16, 2026 · 8:43 PM UTC
• Version: 1.2.0

Overview

The skill appears to do what it says: submit Facebook profile URL collection jobs to Dataify using a Dataify API token, with some privacy and token-use considerations to understand first.

Install only if you intend to use Dataify to collect Facebook profile data by URL. Before running it, make sure you are allowed to collect the profiles you submit, understand that the profile URLs are sent to Dataify, and treat DATAIFY_API_TOKEN as a credential that authorizes actions on your Dataify account.

SkillSpector

By NVIDIA

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
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill instructs the agent to access a locally saved environment token and send data to an external network endpoint, but no explicit permission declaration or user warning accompanies those capabilities. This creates a transparency and consent gap: users may not realize the skill can read local secrets and transmit them off-platform.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger description is overly broad because it activates not only for scraping requests but also for generic mentions of task_id/status, token configuration, and troubleshooting. Broad activation increases the chance the skill is invoked in contexts where the user did not intend to use an external Facebook-scraping service or expose an API token.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill does not explicitly warn that Facebook profile URLs and the user's API token will be transmitted to a third-party service. This omission undermines informed consent and can lead users to share sensitive identifiers or credentials without understanding the data flow to an external processor.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger description is overly broad and includes many generic Facebook collection/scraping phrasings, which increases the chance that the skill is invoked for requests outside its intended scope. Misrouting can cause unintended third-party data submission, accidental token-handling flows, or collection actions when the user only asked informational questions or requested a different Facebook-related task.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to transmit user-provided Facebook profile URLs and an API TOKEN to a third-party service, but it does not require a clear user-facing warning about data transfer, external processing, or the sensitivity of credentials. This can lead users to disclose secrets or submit personal data without informed consent, especially because the workflow encourages token reuse from local storage and operationalizes scraping of profile data.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill metadata enables implicit invocation and describes broad triggering around Facebook profile collection, task IDs, token configuration, and troubleshooting without tight constraints on user intent or authorization context. This can cause the agent to invoke a data-collection capability in situations where the user did not clearly and explicitly request scraping behavior, increasing the risk of privacy-invasive or policy-violating automation.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

- If the user provides a token in the request, use it for this run.
- If no token is provided, first check whether `DATAIFY_API_TOKEN` is already saved locally in the environment.
- If `DATAIFY_API_TOKEN` is saved locally, use it without asking the user to re-enter the token.
- If no token is available locally, tell the user they need to provide a Dataify API TOKEN.
- If the user does not have an API TOKEN, tell them they can register or log in at [Dataify](https://dashboard.dataify.com/login?utm_source=skill) to get one.
- If the user already has an API TOKEN, tell them it is available in the top-right area of [Dataify](https://dashboard.dataify.com?utm_source=skill).

• Confidence: 90% confidence
• Finding: The workflow authorizes the agent to check for and use a locally saved DATAIFY_API_TOKEN 'without asking' the user each time. Even if convenient, silent use of stored credentials is dangerous because it lets the skill act with preexisting authorization and send data externally without an explicit per-use consent step.

VirusTotal

62/62 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.