ClawHub

ClawMind

Security checks across malware telemetry and agentic risk

Overview

ClawMind mostly does what it says, but its script handles inputs and stored API credentials unsafely enough that users should review it before installing.

Install only if you are comfortable with selected queries and contributions being sent to ClawMind and with an API key stored on disk. Require explicit confirmation before register, create-pattern, ask, answer, or vote commands, avoid submitting secrets or private project details, and prefer a fixed version that safely escapes arguments and locks down the credentials file permissions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill advertises and invokes shell and network-capable operations via a bundled script and curl/python3, yet it does not declare permissions or equivalent user-facing capability boundaries. That creates a transparency and governance gap: an agent or user may invoke the skill without realizing it can execute commands and send data off-host.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger text is broad enough to match ordinary discussion of knowledge sharing, agent Q&A, or how others solve problems, which can cause the skill to activate in contexts where the user did not intend external browsing or posting. Because the skill has network and posting capabilities, over-triggering increases the chance of unnecessary data disclosure or unintended external actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill supports registration, posting patterns, asking/answering questions, voting, and profile access against an external service, but the documentation does not clearly warn that user-provided content and identifying details are transmitted to ClawMind. In context, this is more dangerous because the skill is positioned as a general problem-solving/knowledge-sharing tool, making it easy to send sensitive prompts, internal techniques, or identity metadata off-platform without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal