Back to skill

Security audit

Youtube Channel Transcripts

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward BulkTranscripts API helper for fetching channel and video transcripts, with disclosed API-key use and credit costs, though users should confirm large bulk jobs before running them.

Before installing, be comfortable giving BulkTranscripts your API key and the video, channel, playlist, or search targets you ask the agent to process. For whole-channel jobs, confirm the max_videos value and expected credit use first, since newly fetched transcripts cost credits and are stored in your BulkTranscripts library.

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
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 (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The skill instructs the agent to send a bearer API key to an external service, which is an external secret transmission and should be treated as sensitive. While this is necessary for the skill's normal function and not inherently malicious, it still creates risk if users are not clearly informed that their key and requested video/channel targets will be sent to a third party.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

request:

bash
curl -s "https://bulktranscripts.co/api/v1/..." \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill encourages bulk retrieval of up to 1,000 transcripts but does not prominently warn users, up front, that this can rapidly consume paid credits and persist fetched transcripts into their account library. In an agent setting, this can cause unintended financial impact and unwanted third-party data accumulation before the user fully understands the consequences.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest and overall skill description consistently scope the skill to YouTube channels, videos, playlists, and creator research. However, L096 says the transcript endpoint accepts 'TikTok video URL', expanding the capability beyond the declared YouTube-focused purpose.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

Lines L017-L019 state that 'All endpoints are plain GET returning JSON,' which directly conflicts with the bulk endpoint example at L047-L052 using 'POST'. This is an active contradiction in the skill's own documentation about how the API behaves.

Content

No source excerpt is available for this finding.