ClawHub
Back to skill

Security audit

Story Long Analyze

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a story or novel analysis helper whose file reading and output generation are aligned with that purpose, with no evidence of exfiltration or destructive behavior.

Install only if you want an agent to analyze long-form story files. Invoke it deliberately, confirm the file path before analysis starts, and do not give it paths to unrelated private material.

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
95% confidence
Finding
The skill declares very broad natural-language triggers such as '帮我拆这本书', '深度拆解', '系统拆解', and even any provided novel text path as entry conditions. This can cause unintended invocation during ordinary conversation, leading the agent to start file reads, backup/copy operations, and multi-stage output generation without sufficiently explicit user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.