Back to skill

Security audit

Cxz9909 Code Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a Spanish code-analysis assistant whose inspected code reads user-selected source files and prints analysis or generated documentation without hidden network access, file writes, or persistence.

Install this if you want a Spanish-language coding assistant for local code review and documentation suggestions. Review any future refactor, auto-fix, or self-repair action before applying changes, because those capabilities could modify code if implemented by the host agent or a later version.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill advertises capabilities that can affect code and references environment-related capability detection, but it does not declare any explicit tool scope or permissions boundaries. In an agent setting, missing scope declarations can cause overbroad access assumptions and make it unclear whether the skill may inspect sensitive environment data or invoke tools beyond what users expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description promotes refactoring, documentation generation, and automatic assistance without clearly warning that these actions may modify user files. Users may invoke the skill expecting analysis-only behavior, while an agent could proceed with write operations that alter source code or project documentation unexpectedly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The configuration and integration sections describe auto-fix and self-repair behavior, which can lead to automatic code changes without a strong safety boundary or explicit confirmation requirement. In a coding-agent context, this is more dangerous because autonomous modification of source files can introduce defects, overwrite user intent, or be abused to make stealthy changes across a repository.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language user-facing text that fixes the skill's interface to Spanish (Asistente de programación especializado). The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Multiple user-facing CLI messages and help text are emitted only in Spanish, such as usage instructions, analysis summaries, and command descriptions. This enforces a specific language for all users without offering a locale selection or documenting a justified restriction.

Content

No source excerpt is available for this finding.