ClawHub
Back to skill

Security audit

Brazil

Security checks for vulnerabilities and agentic risk

Overview

This is a Brazil travel-planning skill with scoped local trip memory and no evidence of hidden execution, network access, or data exfiltration.

Before installing, be aware that the skill stores Brazil trip context locally in ~/brazil/memory.md and may reuse it in later sessions. Review or delete that file if you do not want passport/nationality, trip dates, budget, dietary, mobility, or other preferences retained.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · customs-and-border.md (reported line 13)May include surrounding context.

md
- Carrying expensive electronics without clarity on personal-use versus commercial quantity.
- Assuming food, seeds, or animal products can always move freely.
- Crossing land borders and forgetting that re-entry to Brazil may require the same passport-and-visa logic as first entry.
- Moving with large cash amounts without checking reporting rules.

## Safer Operating Pattern

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to create and maintain a persistent memory file containing user travel context, including passport/nationality, dates, budget, mobility constraints, dietary needs, and other sensitive preferences, without any explicit user notice or consent. Persistent storage of personal data increases privacy risk, especially because returning sessions silently read and reuse the file, which can expose or retain more information than the user expects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The heading 'Safety in Brazil Should Be Operational' sets a locale-specific constraint for the skill content. The file does not indicate that this Brazil-specific framing is optional, user-selected, or justified as a region-specific tool, which can conflict with the policy against forcing a locale without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.