ClawHub
Back to skill

Security audit

Automation Workflows Moss

Security checks for vulnerabilities and agentic risk

Overview

This is a plain instructional skill for planning no-code business automations, with some privacy and scoping cautions users should keep in mind.

Before installing or using this skill, treat any automation that touches customer records, payments, email campaigns, or social posting as sensitive: connect only the accounts and fields needed, test with safe sample data where possible, review logs for exposed personal data, and make sure recurring workflows can be disabled easily.

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
  • 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," "save time," and "reduce manual work," which can cause the skill to activate in many ordinary contexts not specifically requesting workflow-automation help. Overbroad invocation increases the chance of unintended routing, irrelevant advice, and accidental collection or processing of business/process details in contexts where a narrower skill should apply.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill provides extensive guidance for moving customer, payment, CRM, and usage data across tools but does not warn about privacy, consent, least-privilege access, data minimization, or regulatory handling obligations. In automation contexts, users may wire together sensitive systems in insecure ways, leading to overexposure of personal or financial data, unauthorized sharing, or retention of data in third-party platforms and logs.

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.