Safe Smart Web Fetch

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed web-fetch helper that uses third-party cleanup services for URLs it classifies as public, with privacy caveats but no hidden or destructive behavior.

Install only if you are comfortable with ordinary public URLs being sent to external cleanup services. Do not use it for confidential links, private documents, invite/reset URLs, or URLs with identifiers unless you modify the workflow to require explicit approval or force direct fetch only.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: For URLs classified as public, the code automatically sends the target URL to external cleaning services (r.jina.ai, markdown.new, defuddle.md) before attempting a direct fetch. This can disclose user-requested URLs, embedded path/query data that classification misses, and browsing targets to third parties without explicit consent, which is a real privacy and data-handling risk in a fetch skill.

VirusTotal

65/65 vendors flagged this skill as clean.