ClawHub
Back to skill

Security audit

video-transcript-extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward video transcript extraction guide, with expected external API use but no bundled code, persistence, credential access, or hidden behavior.

Before installing, treat extracted transcripts and media links as potentially sent to external platform, ASR, or AI services. Use it only for content you are allowed to process, and avoid private, sensitive, or copyrighted material unless you have permission.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes sending user-supplied video links through platform APIs and potentially processing subtitles/audio via ASR and AI correction, but it does not warn users that their links, media-derived data, and transcript content may be transmitted to external services. This creates a meaningful privacy and compliance risk because users may provide private, sensitive, or copyrighted content without informed consent about third-party processing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill lists 'AI Training: Collect corpus data' as a use case without clarifying consent requirements, ownership restrictions, or whether multilingual content may be reused for model training. That framing can encourage collection or repurposing of transcripts from third-party videos without informed consent, creating privacy, copyright, and policy risks even if the omission appears unintentional.

Content

No source excerpt is available for this finding.