Back to skill

Security audit

Agente Matematica

Security checks for vulnerabilities and agentic risk

Overview

This is a Portuguese math tutoring skill with no executable code, persistence, credential handling, or hidden data flow.

Install this if you want a Portuguese FUVEST math tutor. Be aware it is tailored to a named student context and may activate broadly around math topics, so users who need a general or multilingual tutor may want the publisher to narrow the trigger and language guidance.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
70% confidence
Finding

The skill is written entirely in Portuguese and is targeted to a specific user context, but it does not explicitly offer the user a language choice or state that Portuguese is a required locale. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition is broad enough to trigger on virtually any mention of mathematics, which can cause the skill to activate outside clear user intent. In a multi-skill environment, this increases the risk of over-collection of context, unnecessary priority escalation, and interference with other agents or normal conversation flow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.