ClawHub

Iso42001 Aims Readiness

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly coherent, but it sends sensitive AI governance details to ToolWeb and includes a test script that weakens API-key protection.

Review before installing. Use this only if you are comfortable sending organizational AI governance and compliance details to ToolWeb, avoid including regulated or confidential specifics unless approved, and do not run scripts/test-api.sh as-is unless the -k TLS bypass is removed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
97% confidence
Finding
The skill invokes shell execution via curl but does not declare corresponding permissions, creating a capability/permission mismatch. This weakens user and platform transparency and can lead to unexpected external network activity under the guise of a documentation-only skill.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly says the skill will gather details about the organization's AI usage and governance and send them to an external API, but it does not provide a clear privacy notice, data-sharing warning, or guidance on what sensitive information should not be sent. In this context, users may disclose confidential governance gaps, system inventories, regulated-sector details, or compliance weaknesses to a third party without informed consent or data minimization.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to collect and transmit organization name, industry, AI usage, governance maturity, and certification status to a third-party API without a prominent user-facing notice or consent step. These details can be commercially sensitive, and sending them off-platform without explicit disclosure creates privacy, confidentiality, and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal