Dataify Amazon Product List

• Outcome: Pass
• Latest audit: Jul 16, 2026 · 8:42 PM UTC
• Version: 1.2.0

Overview

The skill is a disclosed Dataify task-submission helper that uses one named API token and sends the requested Amazon collection parameters to Dataify, with no hidden persistence or unrelated behavior found.

Install only if you intend to submit Amazon product-list collection jobs to Dataify. Be aware that the skill can use DATAIFY_API_TOKEN from your environment and send your task parameters to Dataify; review the parameters before allowing submission and avoid placing sensitive information in keywords or file names.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill instructs the agent to read a saved environment variable and make an outbound network request, yet no explicit permission declaration is present. That creates a capability/consent gap: a user or platform reviewer may not realize the skill can access locally stored secrets and transmit data to an external service, which increases the risk of unintended secret use or data exfiltration if the skill is triggered unexpectedly or modified later.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger description is broad and ambiguous, matching many natural-language variants for Amazon product list collection. This can cause the skill to activate unexpectedly in unrelated conversations and steer the agent into collecting parameters, handling tokens, or initiating external task submission without sufficiently explicit user intent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill instructs the agent to reuse a locally stored API token automatically, but it does not require notifying the user that a saved credential will be used or obtaining consent at the time of use. In an agent setting, silent reuse of stored secrets can lead to unintended third-party API actions and reduced transparency around credential use.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill directs the agent to send user-supplied parameters and task data to an external Dataify endpoint but does not instruct the agent to warn the user that their inputs will be transmitted to a third-party service. This creates a privacy and data-handling risk, especially if keywords, file names, or other parameters contain sensitive business or personal information.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill enables allow_implicit_invocation without defining meaningful trigger constraints or exclusions in the file, which can cause the agent to invoke this capability in broader contexts than intended. Because the skill can submit external Dataify collection tasks and interact with an API token, unintended invocation could trigger unauthorized scraping actions, unexpected external requests, or accidental use of sensitive credentials.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.