Back to skill

Security audit

Automation Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a plain-language workflow automation guide with sensitive business-app examples, but no hidden code, install actions, or unauthorized persistence.

Install only if you want guidance for building business automations. When connecting real apps, grant the minimum needed permissions, test with non-production or limited data first, review customer/payment data handling, and make sure any live automations can be monitored, paused, and rolled back.

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
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include very broad terms like 'automate', 'automation', and 'save time', which can match many ordinary requests outside the intended scope. This can cause the skill to activate inappropriately and steer users into connecting tools or automating processes without sufficient relevance or safety review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill encourages connecting business apps, CRMs, forms, payment systems, and customer data flows but does not warn about privacy, consent, data minimization, or corruption risks. In this context, users may automate sensitive personal or financial data handling without safeguards, leading to exposure, misrouting, duplication, or compliance issues.

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.