Back to skill

Security audit

Expedia

Security checks for vulnerabilities and agentic risk

Overview

This Expedia skill is coherent and disclosed: it helps with Expedia travel searches and partner workflows while gating bookings and sensitive data use behind explicit approval.

Install this if you want Expedia-focused travel assistance and are comfortable with Expedia receiving your travel search details. Use partner API or booking steps only when you intentionally provide authorized credentials or approve a live booking flow, and review ~/expedia/ if you want to clear saved travel preferences later.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
|----------|-----------|---------|
| `https://www.expedia.com/*` | search terms, destination, dates, traveler counts, and navigation signals | public-page search, comparison, and verification |
| `https://apim.expedia.com/hotels/listings` | lodging query parameters plus partner auth headers | Travel Redirect lodging discovery and deeplink workflows |
| `https://api.ean.com/v3/*` and `https://test.ean.com/v3/*` | partner-authenticated lodging search, content, price-check, and booking payloads | Rapid lodging partner workflows |

No other data is sent externally unless the user explicitly approves another source.
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation rule is broad enough that the skill may auto-engage on loosely Expedia-related travel queries without a clear user request to use this specific capability. That can cause scope creep, unintended persistence of preferences, and inappropriate collection or use of travel-planning context in sessions where the user expected a generic response.

Static analysis

No suspicious patterns detected.