ClawHub
Back to skill

Security audit

Automation Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a plain guidance skill for designing business automations, with no bundled code or hidden execution, though users should apply extra care around customer data, emails, billing, and CRM updates.

This skill is reasonable to install as a workflow-planning guide. Before turning suggested automations on, test with non-production or carefully controlled data, limit connected-account permissions, avoid exposing sensitive customer fields in notifications, and require human review for customer-facing emails, public posts, CRM status changes, and billing/accounting updates.

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
95% confidence
Finding

The trigger phrases are broad and include generic terms like "automate," "automation," and "save time," which can cause the skill to activate in contexts where the user did not specifically request workflow design. Unintended invocation matters here because this skill gives operational guidance affecting external tools, customer data, and business processes, so misrouting can lead to inappropriate or premature automation advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill provides detailed instructions for automating actions across CRMs, email tools, billing systems, and customer communications, but does not warn about validating permissions, protecting customer data, avoiding unintended sends, or testing in safe environments. In this context, missing safety guidance increases the chance of privacy breaches, accidental customer outreach, financial errors, or large-scale propagation of bad data through connected systems.

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 220)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.