Back to skill

Security audit

YouTube Transcript Extractor by AkkuAlle

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for YouTube transcript extraction, with manageable risks around external API use, language defaults, and an optional unpinned package install.

Install only if you are comfortable with the skill using a YouTube API key and sending YouTube video identifiers or URLs to YouTube-related services. Prefer an isolated environment for the optional Python package workflow, pin package versions where possible, and specify transcript language when German is not intended.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:47
Finding

Unpinned Third-Party Package Installation and Execution

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description explains how to use a YouTube API key and external tools but does not warn users that invoking the skill may transmit video identifiers or URLs to third-party services and consume configured credentials. This creates a consent and transparency problem, especially in agent environments where users may not realize external services are being contacted automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill specifies loading a German transcript by default without indicating that this is optional or dependent on user preference. Hard-coded language behavior can silently retrieve the wrong transcript, omit available content in other languages, or cause misleading downstream summaries and blog content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The alternative commands hard-code the German locale using '--sub-lang de' and languages=['de'], which forces retrieval behavior that may not match user intent or the source video. In this context the risk is primarily integrity and usability: generated analysis may be incomplete, translated unexpectedly, or fail when German subtitles do not exist.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation guidance uses broad example phrases such as analyzing a video or extracting key points, which can cause the skill to trigger in situations where the user did not specifically request transcript retrieval or external fetching. In this skill’s context, that can lead to unintended network access and use of configured credentials when the user may have only wanted general discussion.

Content

No source excerpt is available for this finding.