ClawHub
Back to skill

Security audit

Automation Workflows Local

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward automation-planning guide with no executable code, but users should apply normal privacy and approval checks before connecting business tools.

Before installing, treat this as a planning guide: review any automation before turning it on, grant the smallest account permissions available, test with non-sensitive or limited data first, and add human review for public posts, customer emails, invoices, payment updates, or bulk CRM changes.

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
97% confidence
Finding

The trigger phrases are broad enough to activate on common conversational language like 'save time' or 'automation,' which can cause unintended invocation of this skill outside narrowly relevant contexts. That increases the chance the agent will apply workflow-building guidance when the user did not explicitly ask for automation, creating misfires and potentially unsafe account-connection or action recommendations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This section encourages connecting accounts and moving operational data across tools, but it does not warn about least-privilege access, sensitive data handling, duplicate actions, or validation before writes. In an automation context, omissions like these can lead to privacy leaks, corrupted records, accidental notifications, or unintended business actions at scale.

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.