ClawHub
Back to skill

Security audit

Automation Workflows 0.1.0

Security checks for vulnerabilities and agentic risk

Overview

This is a plain workflow-automation guide with business-data examples, not executable code or hidden behavior.

Before installing, be aware that this skill may suggest automations touching customer, lead, payment, CRM, email, Slack, and public posting workflows. Use least-privilege app connections, test with limited data, add approvals before customer-facing messages or financial/accounting updates, and avoid sending sensitive customer or payment details into chat notifications unless necessary.

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
96% confidence
Finding

The trigger list includes very broad phrases such as 'automate', 'automation', 'save time', and 'reduce manual work', which are common in ordinary conversation and can cause the skill to activate outside narrowly intended contexts. Over-broad activation is dangerous because it can route unrelated user requests into workflow-automation guidance, increasing the chance of inappropriate actions, data handling suggestions, or user confusion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill repeatedly recommends moving customer, lead, payment, and usage data across CRMs, spreadsheets, email tools, Slack, and other systems without providing privacy, consent, least-privilege, or data-validation safeguards. In this context, that omission is risky because users may implement automations that leak personal or financial data, propagate bad data across systems, or trigger unintended customer-facing 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.