Back to skill

Security audit

Offline Airport Lounge Finder - Comparison Map

Security checks for vulnerabilities and agentic risk

Overview

This is a local read-only Priority Pass catalog skill, but its npm dependency setup is incomplete and unpinned, so it should be reviewed before installation.

Install only in a restricted environment until the publisher adds a minimal package.json, pins @modelcontextprotocol/sdk and zod, and includes a lockfile. Treat the catalog as a stale offline snapshot, and be aware it covers broader Priority Pass airport experiences, not only lounges.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:8
Finding

Unpinned and Incomplete Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
- Offline-only runtime: use bundled `assets/catalog.json` via local stdio MCP.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest describes offline access to a bundled 'Priority Pass lounge catalog' for lounge lookup, filtering, briefs, and comparisons. But the data explicitly includes non-lounge categories in filters.types such as EAT, REFRESH, REST, and UNWIND, and numerous entries are restaurants, spas, sleep/suite products, and gaming/work pods rather than lounges, which broadens the skill’s actual subject matter beyond what the description claims.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Many records include detailed benefit-redemption rules, visit-charge mechanics, guest charging rules, issuer/card-program restrictions, and merchant credit terms embedded in conditions. That goes beyond basic offline lounge lookup and facility filtering, and turns the dataset into a broader entitlement/commerce rulebook not reflected in the manifest’s narrower stated purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This JSON repeatedly embeds https://my.prioritypass.com/en-GB/... links, which forces a specific English (UK) locale in user-visible resources. Because the file provides no opt-in, fallback, or locale-neutral alternative, it conflicts with the rule against imposing a language/locale choice without user consent.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest describes this skill as specifically for offline or air-gapped use, but the exported constant is named ONLINE_SERVER_INFO and identifies the server as 'pp-lounge-map'. While the code itself remains local-only, this inline identifier/documentation contradicts the stated offline intent and could mislead maintainers or integrators about the deployment model.

Content

No source excerpt is available for this finding.