Back to skill

Security audit

Seguranca Auditoria

Security checks for vulnerabilities and agentic risk

Overview

This is a Portuguese-language security-audit guidance skill with no bundled executable code or hidden privileged behavior.

Install only if a Portuguese-language audit checklist/reporting skill fits your workflow. Treat it as guidance unless the surrounding platform supplies the referenced audit command, because this package itself does not include scanner code.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file uses Portuguese-only naming and description text and explicitly tags the skill as 'portugues' and 'brasil'. This creates a language/locale restriction in the skill's natural-language interface without stating that users may choose another language or locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description states that the skill "Gera relatórios detalhados em português," which indicates a fixed output language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified; the manifest does not present this as optional or required for a region-specific compliance purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.