ClawHub
Back to skill

Security audit

Dataify YouTube Transcript By ID

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned Dataify integration that submits YouTube transcript jobs using a local API token, with disclosed external calls and no hidden persistence or destructive behavior.

Install only in an environment where DATAIFY_API_TOKEN is your own Dataify token, and expect the skill to contact Dataify and potentially consume account credits when you ask it to collect transcripts. Be cautious with ambiguous Dataify requests because implicit invocation is enabled.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent to read a saved API token from the environment and make outbound network requests, yet no permissions are declared. This creates a transparency and governance gap: users and policy engines may not realize the skill can access credentials and external services before it runs.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The default prompt is broad enough to encourage automatic invocation for generic 'Dataify collection' requests, especially combined with implicit invocation. This can cause the agent to call the YouTube transcript collection skill without sufficiently confirming that the user specifically wants transcript-by-ID retrieval, increasing the risk of overbroad or unintended external actions.

Ssd 3

Medium
Confidence
87% confidence
Finding
Instructing the agent to automatically reuse a locally stored `DATAIFY_API_TOKEN` without re-prompting can cause silent credential use across tasks or users in a shared environment. That increases the risk of unintended account actions, billing/credit consumption, and cross-session secret misuse when identity or authorization context is ambiguous.

Ssd 3

Medium
Confidence
90% confidence
Finding
The instruction to check for and continue with a saved API token semantically encourages secret retrieval from local state as a default behavior. In multi-user, shared-agent, or unclear-trust contexts, that can lead to unauthorized use of another principal's credential and accidental disclosure of account-linked actions.

Static analysis

No suspicious patterns detected.