Back to skill

Security audit

youtube-playlist-transcripts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for fetching YouTube playlist transcripts through BulkTranscripts, with expected third-party API use and no hidden local execution or persistence.

Before installing, understand that using this skill sends the playlist or video URL or ID, transcript request parameters, and your BulkTranscripts bearer token to bulktranscripts.co. Use care with private, unlisted, or sensitive playlists, and avoid pasting API keys into places where they may be logged.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says to use the skill when the user 'shares a playlist link', 'wants a lecture series or course turned into study notes', or 'needs playlist transcripts as text'. These triggers are broad natural-language cues and do not define clear boundaries or negative examples, which could cause the skill to be invoked in situations beyond the intended YouTube-playlist transcript workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends playlist/video URLs and transcript request data to a third-party service but does not clearly warn the user before doing so. This can cause unintentional disclosure of viewing interests, private or sensitive playlist identifiers, and API-linked activity to an external provider without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The skill is explicitly designed to transmit user-supplied playlist/video references and an API bearer token to an external service. While this is expected functionality, it is still a real data egress path and becomes risky if users provide sensitive URLs, private playlist links, or if the environment exposes the API key to untrusted workflows.

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"

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The parameter documentation states 'language (default en)', which establishes English as the default language behavior. This can conflict with language/locale choice expectations because the documentation does not instruct the agent to confirm or preserve the user's preferred language before defaulting to English.

Content

No source excerpt is available for this finding.