ClawHub
Back to skill

Security audit

Youtube Playlist Transcripts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using a third-party transcript API, with privacy considerations but no hidden or destructive behavior.

Install only if you are comfortable sending playlist or video links and transcript requests to BulkTranscripts with your API key. Do not submit private or sensitive playlists unless you are comfortable exposing them to that service, and think carefully before changing a private playlist to unlisted.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Content
request:

```bash
curl -s "https://bulktranscripts.co/api/v1/..." \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"
```
Confidence
89% confidence
Finding
The skill directs the agent/user to send playlist URLs, video identifiers, and a bearer API key to an external third-party service. External transmission is expected for this skill's purpose, but it still creates a real confidentiality risk because user-provided content and authentication material are shared outside the local environment.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to change a private playlist to unlisted in order to process it, but does not warn that unlisted playlists become accessible to anyone with the link and may expose titles, contents, and associated metadata to a third-party service. This creates a privacy and data-sharing risk, especially if the playlist contains sensitive educational, work, or personal material.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The documentation states that the `language` parameter defaults to `en`, which imposes a language choice without indicating user selection or opt-in. This can conflict with language or locale policy expectations when the user has not requested English specifically.

Static analysis

No suspicious patterns detected.