ClawHub

t

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent and not malicious, but it can guide agents to install third-party skills globally while skipping confirmation prompts.

Review this skill before installing. It appears intended for legitimate skill discovery, but only allow installs after seeing the exact skill name, source, and reason for installation. Prefer manual or non-auto-confirm installation for unfamiliar publishers, and remember that global installs can affect future agent sessions.

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

Medium
Confidence
93% confidence
Finding
The skill description says it should be used whenever users ask broad questions like 'how do I do X' or want added functionality, which overlaps with many ordinary requests. This can cause the skill to trigger too often and steer the agent toward skill discovery and installation workflows even when the user did not explicitly ask to modify their environment.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation conditions include ambiguous cases like 'can you do X' and general interest in help for a domain, without clear boundaries distinguishing normal assistance from package discovery. In practice, this increases the chance of unnecessary invocation and may push users toward third-party skill installation based on weak signals.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill recommends `npx skills add <owner/repo@skill> -g -y`, which installs code globally and suppresses confirmation prompts without an explicit safety warning, provenance check, or permission gate. Because skills may come from GitHub or other external sources, this lowers friction for executing unreviewed third-party content and increases the risk of supply-chain compromise or unintended system changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal