ClawHub

Uncommon Favor

Security checks across malware telemetry and agentic risk

Overview

The skill content is a non-executable memoir coaching guide, but its published metadata unexpectedly declares wallet and sensitive-credential needs that do not fit the artifacts.

Review the listing carefully before installing. The skill itself appears content-only, but it should not need a wallet, crypto access, or sensitive credentials; do not provide any such information to use it. Expect it may activate on broad basketball, leadership, service, or discipline conversations unless those triggers are narrowed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes very generic terms such as "basketball," "community," "service," and "discipline," which can cause the skill to activate in many unrelated conversations. Over-broad activation can hijack user intent, surface irrelevant guidance without consent, and increase the chance that other instruction-heavy content in the skill is injected into normal chat flows.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The instruction to trigger when a user "just installed this skill or doesn't know how to start" is ambiguous and encourages unsolicited invocation. This can cause the agent to interrupt unrelated onboarding or general help flows, forcing proactive output the user did not request and weakening user control over when the skill is applied.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal