Security audit

MikroTik Encyclopedia

Security checks for vulnerabilities and agentic risk

Overview

This MikroTik helper is a disclosed documentation-cache and note-taking workflow; the main caution is that local notes may contain sensitive network details.

Install/use this only in a private workspace. Before live device access or configuration changes, confirm the target and intended action. Keep .MikroTik-Encyclopedia out of shared repos/backups unless reviewed, and do not store passwords, tokens, private URLs, management addresses, or unnecessary topology details in notes.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:59
Finding: Plaintext Persistence of Sensitive Infrastructure and Access Metadata
Content: View full analysis
.md` for: - device purpose - management access path - role in topology - sensitive boundaries - discovered quirks ### Pattern notes Use `.MikroTik-Encyclopedia/notes/patterns/.md` for: - recurring RouterOS command patterns - repeated gotchas - safe command sequences - environment-specific design conventions ### Inventory files Use `.MikroTik-Encyclopedia/inventory/` for: - topology - access inventory - documentation index ``` `scripts/init_workspace.py:7-10` creates dedicated plaintext inventory files: ```python SEED_FILES = { 'inventory/access.md': '# MikroTik Access Inventory\n\nStore MikroTik device access notes here.\n', 'inventory/topology.md': '# MikroTik Topology\n\nStore environment-specific MikroTik topology notes here.\n', 'inventory/doc-index.md': '# MikroTik Cached Doc Index\n\nTrack especially useful cached official-doc pages here when helpful.\n', ``` ### Technical Analysis The Skill deliberately creates durable plaintext storage for device names, roles, topology, management access paths, and ...[truncated 2484 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The skill presents itself as a broad MikroTik operational workflow, yet the content only defines workspace initialization, doc caching, and note-taking conventions rather than real troubleshooting or device interaction logic. This overclaiming is dangerous because operators may rely on the skill in sensitive networking contexts under false assumptions about its validation, safeguards, or actual capabilities.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The skill presents itself as a broad MikroTik operational workflow, yet the content only defines workspace initialization, doc caching, and note-taking conventions rather than real troubleshooting or device interaction logic. This overclaiming is dangerous because operators may rely on the skill in sensitive networking contexts under false assumptions about its validation, safeguards, or actual capabilities.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill clearly instructs network access to help.mikrotik.com and local file writes under .MikroTik-Encyclopedia/, but it declares no explicit tool scope or permissions boundary. That creates an authorization ambiguity where an agent may perform network fetches and persist data without the user being clearly informed or the platform enforcing a least-privilege policy.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly allows live SSH/API work and persistent writes to local notes and caches, but it does not require an upfront warning or confirmation before touching devices or modifying workspace data. In a router-management context, silent writes or unannounced live access can affect operational records, expose sensitive topology details, or lead to risky interactions with production infrastructure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The workflow explicitly directs the agent to cache official documentation and maintain device notes, pattern notes, and inventory files that can include management access paths, topology, sensitive boundaries, and device-specific quirks, but it provides no safeguards for handling sensitive operational data. In a MikroTik administration context, these artifacts can expose network structure and administrative access details to other workspace users, downstream tools, or source control if stored insecurely.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.