Back to skill

Security audit

youtube-channel-transcripts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using a disclosed third-party transcript API, with no local install hooks or hidden behavior found.

Before installing, understand that this skill relies on a third-party service: you will provide a BulkTranscripts API key, send requested YouTube/TikTok references to bulktranscripts.co, and fetched transcripts may be stored in that account's library. Check credit use before running large channel jobs.

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

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"

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

Lines L017-L019 state that all endpoints are plain GET requests, yet the documented bulk job example at L049-L052 uses POST to /api/v1/bulk. This is a direct mismatch between the skill's stated interface behavior and its own later-described behavior.

Content

No source excerpt is available for this finding.