ClawHub
Back to skill

Security audit

Ultimate Flashcards / Podcasts Tutor

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward EchoDecks API client for managing study decks, but users should understand it sends study content to EchoDecks and can change account data or use credits.

Install only if you trust EchoDecks with the study content you provide. Treat ECHODECKS_API_KEY as a secret, do not paste private health, business, or personal data into prompts unless you intend to send it to EchoDecks, and review any agent action that creates content, submits reviews, or may consume account credits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation explicitly describes use of a service-level API key and endpoints that expose sensitive user information such as email, credit balance, and study data, but it provides no safeguards around key storage, least-privilege usage, or restrictions on exposing returned data. In an agent skill context, this is dangerous because skills often automate requests and may log, embed, or mishandle service credentials, turning the documented API into a pathway for unauthorized access to user data across accounts.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README advertises API-backed deck management, AI card generation, and podcast synthesis using an external API, but it does not clearly disclose that user-provided topics, notes, or study content will be transmitted off-platform to a third-party service. This creates a real privacy and data-handling risk, especially because the stated use cases include potentially sensitive domains like health informatics and cardiology, where users may paste confidential or regulated content.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The README instructs users to create and export an API key but gives no guidance on secure credential handling, increasing the chance that users will expose the key through shell history, shared environments, screenshots, or improper storage. While using an environment variable is common practice, the lack of warnings or handling guidance still represents a legitimate security weakness in documentation.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill exposes tools that can create decks, generate cards, generate podcasts, and submit reviews, and the description explicitly notes that some actions consume credits. However, the skill description does not clearly warn users that invoking these tools can modify account data and incur paid or quota-based costs. This creates a real risk of unintended account changes and unauthorized credit consumption, especially in agent-driven workflows where tool calls may be triggered with limited user awareness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.