ClawHub
Back to skill

Security audit

impactful-writing

Security checks across malware telemetry and agentic risk

Overview

The skill is a text-only writing helper, but its catalog metadata claims wallet, purchase, crypto, and sensitive-credential capabilities that do not fit the artifacts.

Treat this as a writing and editing advice skill only. Do not grant it wallet, payment, crypto, or credential-related permissions unless the publisher explains why those capabilities are present and narrows them to a clear, user-controlled workflow.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is extremely broad and overlaps with many ordinary writing or editing requests across social posts, emails, documentation, comments, and updates. In agent systems that auto-route by description, this can cause over-invocation, letting the skill shape responses in situations where the user did not explicitly request it, which increases unintended prompt influence and policy-surface expansion.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.