Security audit

Skiplagged Flights

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Skiplagged travel search, but it installs an unpinned executable npm tool and may trigger broadly for general travel planning.

Install only if you are comfortable with a Node-based helper CLI being installed and used to send travel search details to Skiplagged's public MCP service. Prefer a reviewed, pinned mcporter version or a sandboxed install, and invoke the skill only for searches that need Skiplagged flight, hotel, car, destination, or fare-calendar results.

A.I.G

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:5
Finding: Unpinned Executable npm Dependency Creates a Supply-Chain Risk
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description contains very broad trigger phrases such as general trip planning, destination exploration, hotels, and flights, which can cause the agent to invoke this skill for a wide range of common travel queries. This is risky because an over-broad auto-trigger may route user requests to an external public MCP service unnecessarily, increasing data exposure and reducing least-privilege tool selection.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.