ClawHub
Back to skill

Security audit

Ruflo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a short Ruflo reference guide with no bundled executable code, but it is incomplete and should be treated as guidance rather than an operational harness.

Installers should understand that this package appears to be an incomplete wrapper or pointer to Ruflo rather than a functional bundled harness. Before relying on it for real orchestration, verify the upstream project, scripts, memory behavior, security controls, and any permissions requested by separately installed Ruflo components.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation guidance is overly broad: 'when the user asks about multi-agent coordination, swarm orchestration, or agent memory' can match a wide range of normal conversations and cause the skill to be invoked outside clearly intended contexts. Because this skill references scripts and a complex multi-agent framework spanning machines and trust boundaries, unintended activation increases the chance of irrelevant or unsafe tool use, misleading guidance, or unnecessary exposure to higher-risk capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This line presents part of the skill description in Traditional Chinese without indicating that the user can choose their preferred language. That creates a language/locale policy concern because the skill content implicitly enforces a specific language in a general-purpose description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.