ClawHub
Back to skill

Security audit

SIPOC技能工具

Security checks across malware telemetry and agentic risk

Overview

This skill coherently helps create SIPOC process diagrams, with no evidence of hidden persistence, credential access, network exfiltration, or destructive behavior.

Install only if you want a local SIPOC diagram helper. Avoid feeding it untrusted or attacker-supplied text until HTML escaping is added, and review generated HTML before sharing or opening files built from external business data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script builds HTML with Python f-strings and inserts untrusted fields such as process_name, process_id, item names, descriptions, and step text directly into element content without HTML escaping. If attacker-controlled JSON is rendered and the output is opened in a browser, injected markup or JavaScript can execute, turning this diagram generator into an XSS-capable HTML emitter; the skill context makes this more concerning because generating browser-opened documents is its core function, so untrusted business data is likely to flow into the output.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases include broad terms such as '创建流程图' and '梳理输入输出', which can overlap with ordinary conversation and unrelated workflow requests. This can cause unintended activation of the skill, leading the agent to collect extra business-process details, generate files, or invoke scripts in contexts where the user did not explicitly request SIPOC behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.