Back to skill

Security audit

Optimacros

Security checks for vulnerabilities and agentic risk

Overview

This is a Russian-language Optimacros helper skill made of Markdown notes, with no executable install behavior or hidden data access found.

Install this only if Russian-language Optimacros assistance is useful to you. Because it advises on access rights, scripts, DCA, exports, and service accounts, review any proposed Optimacros permission or automation changes before applying them in a real model.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Инструкция 'Пиши по-русски' принудительно ограничивает язык ответа без учета запроса пользователя, что может нарушать ожидаемое поведение агента и приводить к ошибкам интерпретации, недоступности или скрытому игнорированию пользовательских предпочтений. Это не прямой exploit-код, но является небезопасным policy-override внутри skill, потому что меняет канал взаимодействия и может мешать корректной и безопасной обработке запросов.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Russian, starting at L003 and continuing throughout the document. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no locale constraint or language choice is documented.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and the entire note are written in Russian, and the file does not indicate that Russian is optional or that the skill is intended only for a Russian-speaking or region-specific audience. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire note is written in Russian and does not indicate that the skill is intentionally limited to Russian-speaking users or a specific locale. Under the language/locale policy, forcing a specific language without user opt-in or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.