ClawHub
Back to skill

Security audit

Dataify Instagram Reels

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it submits user-selected Instagram Reel collection jobs to Dataify using a Dataify token, with no hidden persistence or unrelated data access found.

Install only if you intend to submit Instagram Reel collection tasks to Dataify. Be aware that your Instagram URLs, filters, file name, and Dataify account token will be used for external Dataify Builder requests, and make sure you are authorized to collect the target data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
97% confidence
Finding
The skill is designed to access a locally saved API token from environment variables and send user-supplied Instagram URLs and parameters over the network to Dataify, yet it declares no permissions. That creates a transparency and consent gap: users and reviewers are not clearly informed that the skill can read local secrets and transmit data to an external service.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger conditions are overly broad because they activate not only for Instagram Reel collection requests but also for generic mentions of task_id/status, token configuration, or troubleshooting. That can cause the skill to engage in contexts where the user did not clearly intend external API use or secret handling, increasing the chance of accidental token solicitation or unintended data submission.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to submit Instagram URLs and related parameters to a third-party endpoint but does not clearly disclose that these inputs will be transmitted outside the local environment. This can expose potentially sensitive targets, account URLs, or collection criteria without informed user consent.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger description is extremely broad and includes many generic scraping/collection phrases in both English and Chinese, which increases the chance the skill activates for ambiguous user requests that may not clearly indicate intent to use this specific third-party data collection service. In context, this is risky because the skill can lead to submission of Instagram scraping tasks and token-handling flows, so accidental invocation could cause unintended third-party data transfer or guide users into potentially non-compliant collection behavior.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to submit Instagram Reel collection jobs to a third-party platform but does not clearly warn that URLs and retrieved data will be sent to Dataify, nor does it mention possible privacy, terms-of-service, or account/platform compliance implications. In this context, the omission is material because the skill is specifically designed to automate social-media scraping workflows and handle API tokens, so users may proceed without informed consent about external transmission and policy risk.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill enables implicit invocation while advertising a very broad trigger surface in metadata and description, which can cause the agent to call this skill for loosely related requests about Instagram reels, scraping, URLs, status checks, or configuration. Because the skill submits external Dataify tasks, unintended activation can lead to unauthorized data collection actions, accidental API usage, and user actions being routed to a third-party service without sufficiently explicit consent.

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 instruction to automatically use a saved DATAIFY_API_TOKEN without asking the user to re-enter it enables autonomous use of an existing secret. While convenient, it can cause external actions to be performed under stored credentials without fresh confirmation, which is risky in ambiguous or delegated-use contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.