Back to skill

Security audit

Arquitecto Categórico

Security checks for vulnerabilities and agentic risk

Overview

This is a Spanish-language category-theory architecture skill that reads bundled Markdown references and does not show code execution, persistence, credential use, or data exfiltration behavior.

Install this skill if you want technical Spanish assistance for formal data modeling and architecture review. Expect it to answer in Spanish and to produce schemas, diagrams, API contracts, or audit reports; review generated DDL or migration plans before applying them to real systems.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (24)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

La instrucción "Escribir en espanol tecnico" fija un idioma de salida de forma obligatoria. Según la política indicada, forzar un idioma específico sin opción del usuario constituye una violación de política lingüística.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown instructions are written entirely in Spanish and direct the user to perform actions in that language, but the file does not offer an opt-in choice of language or explain that the skill is region- or locale-specific. This can violate language/locale policy when users or downstream skills expect neutral or user-selectable language behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L03 instructs the user in Spanish ('Usar este archivo...'), and the rest of the file consistently requires Spanish phrasing for the workflow. This is a natural-language locale constraint with no indication that the user may choose another language or that the limitation is justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown skill uses Spanish throughout its operational guidance, which can amount to a language policy violation when the skill forces a specific language without user opt-in. The file does not indicate that Spanish is optional, configurable, or justified as a region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file is entirely in Spanish and provides operational routing instructions without any language choice or opt-in, which can cause users to misunderstand mode selection, clarification gates, and hand-off rules. In a skill that influences architecture, schema, and audit decisions, this raises the risk of incorrect or unintended actions due to language mismatch rather than direct code execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file's operational instructions are written in Spanish and direct the model's behavior in that language, but there is no indication that the user can choose another language or opt in to this locale. This creates a language/locale policy concern because the skill effectively constrains interaction language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructional content is written entirely in Spanish and provides no indication that the user can choose another language or that the skill is intentionally limited to Spanish-speaking contexts. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

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’s instructional text is written entirely in Spanish (for example, 'Usar este mapa', 'No editar', 'Empezar siempre'), which effectively imposes a specific language for operation. The policy allows locale constraints only when they are explicitly justified or when the user is given a choice, neither of which is present here.

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.

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.

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.

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
91% confidence
Finding

The text specifies the agent as "Arquitecto Categórico," a Spanish-language identity, but does not indicate that users can choose the language or opt into Spanish output. This can violate language/locale policy when a skill implicitly enforces a language preference without offering alternatives.

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.

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.

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.

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.

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.

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.

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.

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.

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

This markdown skill uses Spanish throughout its operational instructions, which can amount to a language policy violation when the skill forces a specific language without user opt-in. The file does not state that it is region-specific, nor does it offer an alternative language or any user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all operational documentation in Spanish, and there is no indication that users may opt into another language or that the skill is intentionally limited to a Spanish-speaking context. Under the policy for natural-language violations, forcing a specific language without user choice is reportable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.