ClawHub
Back to skill

Security audit

Travel Biz

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Chinese-language travel reimbursement helper, with expected local storage of travel and expense records but no hidden execution, exfiltration, or persistence behavior found.

Before installing, make sure you are comfortable storing receipts, reimbursement forms, travel plans, and exports locally under ~/travel-biz. Use a private, access-controlled location, avoid shared devices for sensitive business expenses, and delete outdated exports or reports when they are no longer needed.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly stores travel records, receipts, reimbursement forms, and company-specific templates in a predictable local directory, but provides no warning that these files may contain sensitive personal, financial, and business-travel data. This increases the chance users will retain unencrypted artifacts on shared or unmanaged devices, leading to unintended disclosure through local compromise, backup syncing, or casual access by other users.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · scripts/test.sh (reported line 3)May include surrounding context.

sh
#!/bin/bash
echo "🧪 测试 travel-biz..."
echo "  SKILL.md: ✅ $(wc -c < /root/.openclaw/workspace/skills/travel-biz/SKILL.md) bytes"
echo "    travel: ✅"
echo "    expense: ✅"
echo "    receipt: ✅"

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill advertises exporting reimbursement data to PDF and Excel without warning that exported files are easy to copy, email, sync, or leave behind in insecure locations. Because reimbursement documents often contain names, itineraries, amounts, receipts, and tax details, unguarded export features can expand the exposure surface beyond the application itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest includes the author value "智美人团队" in Chinese, which indicates a language-specific presentation without any accompanying opt-in or locale choice. Under the language/locale policy rule, natural-language metadata that forces a specific language can be a policy concern when no alternative or user choice is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script's user-facing echo statements are written in Chinese, including status and success messages, with no indication that the skill is region-specific or that users can opt into another language. This is a natural-language policy concern because it imposes a specific language on users without choice or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.