ClawHub
Back to skill

Security audit

Skill Workflow Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed workflow-orchestration prompt that can coordinate other skills, but it contains no executable payload, persistence, hidden behavior, or credential handling.

Install this only if you want a skill that may coordinate several other skills from one natural-language request. Before allowing workflows that send messages, publish content, save data, or trigger reminders, confirm each externally visible or state-changing step and check which downstream skill will perform it.

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 (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is designed to auto-trigger on broad natural-language descriptions involving multi-step tasks, which can cause unintended invocation for ordinary user requests. Because it can chain multiple downstream skills, including sensitive actions like messaging or email, ambiguous activation materially increases the risk of unauthorized or surprising side effects from misclassification or prompt injection flowing through the workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.