ClawHub

Skill

Security checks across malware telemetry and agentic risk

Overview

The skill’s security-checking purpose is coherent, but its checker scripts have a local command-execution risk if the external API response is malicious or compromised.

Review before installing. The skill appears intended to provide security checks, but users should be comfortable sending checked skill names to checksafe.dev and should avoid relying on the included scripts until the JSON parsing is fixed to pass API responses as data, not as executable Python source.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Low
Confidence
88% confidence
Finding
The manual trigger phrases are broad enough to match common user requests such as 'is this safe', 'can I trust this', or 'check this skill', which can cause the skill to activate in ordinary conversation outside a narrowly scoped install-review workflow. In a security-scanning skill this is less dangerous than in a data-access skill, but it still increases the chance of unintended invocation, routing errors, or attacker-crafted phrasing that forces this skill to run when the user did not explicitly request it.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger guidance is extremely broad (`always use`, many generic safety phrases, and pre-check on install), which can cause the skill to be invoked in contexts the user did not explicitly intend. Over-broad invocation increases the chance of unnecessary shell/network actions and may crowd out more appropriate verification workflows.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The script sends each user-supplied skill slug to a third-party service at checksafe.dev without clearly disclosing that those inputs will be transmitted off-box. While the data is not highly sensitive by itself, requested slugs may reveal user interests, planned installations, or internal/private skill names, creating a privacy leak and possible metadata exposure.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal