ClawHub
Back to skill

Security audit

Dataify Facebook Events

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed Dataify wrapper for submitting Facebook event collection tasks, with expected token and network use scoped to that purpose.

Install only if you intend to let the agent create Dataify Facebook event collection jobs. Review the selected mode, URLs, and file name before submission, and remember that an existing DATAIFY_API_TOKEN may be used for the request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to access environment variables and make outbound network requests, but no declared permissions are present to bound or disclose those capabilities. This weakens least-privilege controls and can lead to unintended token use or external data submission without transparent authorization boundaries.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger conditions are very broad and include generic scraping, collection, troubleshooting, token configuration, and multilingual phrasing, which increases the chance the skill activates in contexts the user did not clearly intend. Overbroad invocation can cause the agent to steer users into external task submission flows or credential-handling behavior when a narrower informational response would be safer.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill enables implicit invocation with no visible trigger constraints, while its description covers a broad set of user intents including scraping/collection requests and troubleshooting. That broad auto-activation surface can cause the skill to run in contexts the user did not clearly intend, potentially submitting external Dataify tasks or handling sensitive URLs/tokens without sufficiently explicit confirmation.

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
84% confidence
Finding
The skill authorizes use of a previously saved API token from the environment without re-prompting the user. In a multi-user, shared-session, or ambiguous-intent context, this can trigger external actions under stored credentials that the current user did not knowingly approve.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.