ClawHub

Beepack

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Beepack search helper, but it also tells the agent to post feedback and code diffs to Beepack without clear user review or redaction guidance.

Install only if you are comfortable with the agent querying Beepack during coding tasks. Require review of any package code before reuse, and do not allow feedback, suggestions, reports, or code diffs to be posted unless you have approved the exact content and removed secrets, customer data, internal URLs, and proprietary details.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to post structured feedback to an external service, including free-form fields like adaptations and useCase, which can easily contain internal architecture details, vendor names, workflow descriptions, or other sensitive business context. Because the skill provides no warning, redaction guidance, or minimization requirements, it creates a realistic risk of unintended data disclosure to a third party.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill tells users to submit codeDiff content to an external API, which can directly expose proprietary source code, internal logic, security controls, or embedded secrets if copied from a real codebase. This is more dangerous in context because the skill promotes reuse of production code and improvements to existing packages, making it plausible that users will paste real internal diffs without considering confidentiality or licensing implications.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal