ClawHub
Back to skill

Security audit

Automation Workflows Temp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward no-code automation playbook, with some privacy and scoping cautions users should keep in mind.

Before implementing workflows from this skill, review what customer, payment, and business data each connected service will receive, use least-privilege OAuth/API access, test with limited data first, and keep error notifications and workflow documentation under your control.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad business terms like "automate," "save time," and "reduce manual work," which can cause the skill to activate in many ordinary conversations where the user did not specifically request workflow-design guidance. Over-broad activation increases the chance of inappropriate invocation and can lead the agent to suggest automation steps in contexts involving sensitive operations without sufficient user intent confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill recommends connecting CRMs, payment systems, forms, spreadsheets, email tools, and messaging platforms, but it does not warn that these automations may transfer customer, financial, or business data to third-party services. This omission can cause users to implement workflows that expose sensitive data, violate least-privilege practices, or create compliance issues without realizing the privacy and security implications.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 219)May include surrounding context.

  1. Flag customers with <50% of average usage
  2. Add flagged customers to "At Risk" segment in CRM
  3. Send re-engagement email campaign to at-risk customers
  4. Create task for me to personally reach out to top 10 at-risk customers
text

### Invoice and payment tracking

Static analysis

No suspicious patterns detected.