ClawHub
Back to skill

Security audit

Task Automation Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a single markdown automation guide with disclosed file, API, and scheduling examples that match its stated purpose.

Install only if you want an agent to help design automation. Before running any generated workflow, review exactly which files it can change, what data it sends to which API endpoint, and whether any cron or scheduler entry will continue running after the session.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises very broad trigger phrases such as "automate," "workflow," and "schedule," which can cause it to activate in many contexts beyond the user's intent. Because this skill includes file operations, API calls, and scheduled execution, unintended activation could lead to autonomous actions or recommendations that affect files or transmit data when the user only asked a general question.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill contains examples for outbound API requests and scheduled or recurring tasks, but it does not prominently warn that automation may send data to external services or continue running without immediate user supervision. In an agent setting, omission of these warnings increases the chance that users authorize workflows without understanding privacy, persistence, or operational risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 144)May include surrounding context.

@rate_limit(2) # 2 calls per second def api_call(endpoint, data): return requests.post(endpoint, json=data)

text

**Batch API Calls:**

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.

@rate_limit(2) # 2 calls per second def api_call(endpoint, data): return requests.post(endpoint, json=data)

text

**Batch API Calls:**

Static analysis

No suspicious patterns detected.