ClawHub
Back to skill

Security audit

Al Content Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed content-repurposing skill that fetches user-supplied content and writes generated drafts locally, with no evidence of hidden or malicious behavior.

Install only if you are comfortable letting your chosen runtime fetch the URLs, feeds, videos, or files you provide and save generated drafts under local output folders. Review drafts before posting, enable cron/RSS watching or publishing deliberately, and avoid confidential source material unless your runtime and API configuration keep that data where you expect.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation encourages users to provide remote URLs, YouTube links, podcast feeds, and RSS feeds, and indicates outputs are saved locally, but it does not clearly warn that the skill will fetch third-party content, potentially transcribe media, and write generated files to disk. This can lead operators to run the skill without understanding the network access, content ingestion, and local persistence involved, increasing the risk of unintended data handling, privacy issues, and surprise resource usage.

Static analysis

No suspicious patterns detected.