Security audit

Neckr0ik Automation Templates

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent automation-template generator, but users should review generated workflows carefully before connecting real credentials or production systems.

Before installing or using this skill, treat generated workflows as starter code: review every destination, test with non-production data, use platform secret managers or least-privilege credentials, and be careful with output files because the CLI may overwrite paths you provide.

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
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill documents commands that retrieve, generate, and save workflow files, and it references repository paths such as `templates/` and `scripts/generator.py`, implying file read/write behavior without declaring an explicit tool scope. That mismatch weakens least-privilege controls and can cause users or hosting systems to grant broader filesystem access than intended.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill promotes production-ready automations involving email, CRM sync, backups, webhooks, and API-driven workflows, but it omits safety guidance about privacy, credential handling, and side effects on external systems. Users may deploy templates that process personal or business data without understanding the risk of unauthorized disclosure, unintended messages, or destructive synchronization.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The listed templates include file backup, API sync, CRM sync, and webhook delivery patterns that can automatically copy, overwrite, or propagate data once enabled, yet no warning is given about these operational risks. In an automation-template context, this makes accidental bulk data movement or corruption more likely because users are encouraged to copy and activate workflows quickly.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The customization example shows secrets such as webhook URLs and API keys embedded directly in workflow variables without any warning about secret storage, repository commits, or log exposure. This is dangerous because users may copy credentials into files that are later shared, version-controlled, or imported into third-party automation platforms, leading to account compromise or unauthorized data access.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: This code defines multiple templates that send webhook, CRM, Slack, email, Airtable, and Google Sheets data to external services, but the surrounding docstrings and inline documentation only describe setup steps and do not warn that user or system data may be transmitted off-platform. Under the code-file criteria, these network-transmitting operations lack disclosure beyond their functional names.

Missing User Warnings

Low

Confidence: 95% confidence
Finding: The `get` command writes template output directly to `args.output`, and only reports success after the write; there is no confirmation prompt, overwrite check, or warning that a local file will be created or replaced. The module usage text also does not disclose this file-writing behavior beyond showing an example command.

Missing User Warnings

Low

Confidence: 95% confidence
Finding: The `generate` command saves workflow content directly to the path provided by `--output`, but does not disclose overwrite risk or request confirmation before modifying the filesystem. This is a file-write operation lacking any preventative prompt or explicit warning.

Static analysis

No suspicious patterns detected.