Back to skill

Security audit

Automation Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown playbook for designing business automations; it has broad activation wording and requests exec access, but the inspected artifact does not show hidden execution, persistence, exfiltration, or destructive behavior.

Installers should be aware that this skill may activate broadly because of generic keywords and that it declares exec capability despite being mostly documentation. Use it for workflow-design help, and review any proposed automation before connecting business apps, sending customer emails, modifying CRM records, or handling payment data.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest lists trigger keywords as "save, workflows, implement, automation, design", several of which are common words users may say in many unrelated contexts. The description does not provide scope limits, exclusion conditions, or negative examples to clarify when this skill should or should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file includes substantial Chinese-language metadata and instructions in the description while also presenting English content, but it does not state that language is selectable or user-preferred. This can create an implicit language/locale constraint without opt-in, which matches the policy category for language-choice violations.

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 269)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