ClawHub

Portable Tools

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a portable-tooling guide, but it repeatedly encourages showing exact credential and token values during debugging without redaction guidance.

Review before installing or using. The checklist script itself looks limited, but the written methodology should be changed or followed carefully: do not paste, print, screenshot, or log real access tokens, refresh tokens, keychain password output, or raw credential JSON. Use redacted prefixes/suffixes, lengths, hashes, booleans, and expiry timestamps instead.

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 (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The examples show token-like values and expiration data in plain text as proof of success. Even if partially abbreviated, this normalizes handling secrets in visible output and can lead users to paste real credentials into chats, logs, screenshots, or terminal history where they may be retained or exposed.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The debugging section instructs users to run keychain inspection commands and report which entries contain tokens, without warning that this process can expose credential material or sensitive account metadata. In practice, such guidance can cause disclosure of secrets into transcripts or to an AI assistant, turning troubleshooting into credential exfiltration.

Ssd 3

Medium
Confidence
98% confidence
Finding
The skill explicitly tells users to show exact BEFORE and AFTER values for access tokens and similar credentials. Requesting exact secret values is dangerous because it encourages direct disclosure of bearer tokens, which can often be used immediately by anyone who obtains them.

Ssd 3

Medium
Confidence
98% confidence
Finding
The debugging methodology asks for exact values, counts, and identification of token-bearing entries, which pressures users to inspect and disclose sensitive authentication data during support interactions. In a skill intended for broad reuse, this materially increases the risk of credential leakage to logs, third parties, or LLM conversations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal