ClawHub
Back to skill

Security audit

story-deslop

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed web-fiction editing helper whose local file checks and optional file edits fit its stated purpose.

Install only if you want an opinionated Chinese web-fiction prose editor. For pasted text it may rewrite style aggressively; for file paths it can modify manuscript files, so keep backups or use detection-only wording when you only want a report.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The skill’s declared purpose is narrowly framed as removing 'AI writing traces,' but the body also instructs file-path handling, local file reads/writes, punctuation normalization, and extra diagnostics such as degeneration and placeholder leakage checks. This mismatch is dangerous because users may invoke it expecting a lightweight text-style pass while the agent is authorized to modify local files and perform broader processing than the description suggests.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger set includes broad natural-language phrases such as '这篇太AI了' and '网文去AI味', which are plausible in ordinary conversation and may invoke the skill unintentionally. In this skill, accidental invocation matters more because it can transition into file-oriented analysis and editing workflows, increasing the chance of unexpected modifications or confusing behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.