Dataify Facebook Comment By URL

• Outcome: Pass
• Latest audit: Jul 17, 2026 · 12:35 AM UTC
• Version: 1.2.0

Overview

The skill coherently submits user-reviewed Facebook comment collection jobs to Dataify and discloses its token and network use, with no hidden or destructive behavior found.

Install only if you intend to submit Facebook comment collection jobs through Dataify. Be aware it may use a saved DATAIFY_API_TOKEN and create external Dataify tasks after parameter review, so verify the Facebook URL and limits before allowing a submission.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill explicitly instructs the agent to read a locally saved environment variable (`DATAIFY_API_TOKEN`) and make outbound network requests to a third-party API, but no declared permissions are present. That mismatch weakens the trust boundary: a user or platform reviewer may not realize the skill can access local secrets and transmit data externally. In this context, the behavior is expected for the skill’s function, but it still represents a real capability/permission transparency issue.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description uses very broad trigger phrases covering generic scraping/collection wording, which can cause the agent to invoke this skill in ambiguous contexts without clear user intent. In a tool that can submit external scraping jobs and handle API tokens, accidental invocation increases the risk of unintended data collection actions or unnecessary credential prompting.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill enables implicit invocation, which allows the agent to trigger this external Dataify action without an explicit user request at execution time. Because the skill submits Facebook comment collection tasks and may consume API credentials or cause third-party actions, weak trigger constraints increase the risk of unintended data collection, policy bypass, or accidental use based on ambiguous user phrasing.

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: 82% confidence
• Finding: The skill tells the agent to automatically use a locally saved `DATAIFY_API_TOKEN` without re-prompting the user. That is a form of autonomous use of a stored credential, which can lead to unintended third-party actions or charges if a user did not explicitly authorize this specific submission. The surrounding skill context makes this somewhat less suspicious because the token is directly related to the requested service, but it is still risky because it bypasses per-action confirmation for secret use.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.