clawbox-link-to-docs

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill does what it advertises: fetches a user-provided link and stores the source plus an analysis in Feishu documents.

Install this only if you want the agent to fetch web pages and create Feishu documents in your workspace. Before using it with internal, paywalled, personal, or confidential links, confirm the Feishu destination and sharing permissions because the full source text may be retained there.

SkillSpector

By NVIDIA
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
90% confidence
Finding
The skill explicitly fetches arbitrary external URLs and creates or updates Feishu documents, but it does not state any user-facing consent, scope restriction, or safety checks around network access and document modification. This can lead to unintended data import, SSRF-style access to internal URLs if URL handling is not constrained by the runtime, or overwriting/creating documents in a user's workspace without sufficiently explicit approval.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal