Security audit

travel flight monitor

Security checks for vulnerabilities and agentic risk

Overview

This flight-price monitor mostly matches its purpose, but it asks agents to keep travel-monitoring records, scheduled background checks, and a logged-in browser profile without enough privacy and session-scope controls.

Review before installing if you are not comfortable with recurring background checks, local storage of trip details, or automation using a logged-in browser profile. Prefer a dedicated browser profile for this skill, confirm monitor schedules and thresholds explicitly, and delete monitor records when 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

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 (5)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly stores flight-monitor data under a persistent local path, including route, travel date, threshold, and price history, but does not disclose this retention behavior to the user or offer consent/retention controls. Travel itinerary data can be sensitive because it reveals future movement patterns and habits, and persistent storage increases the risk of unintended disclosure to other local users, tools, or later agent actions.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill instructs use of a logged-in browser profile for automation without warning that the automated browser session may have access to existing cookies, account pages, personal data, and authenticated actions. Even if the current intent is only flight lookup, running automation in a logged-in profile broadens exposure and can accidentally leak or misuse session data if the site redirects, prompts, or changes behavior.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: This markdown file presents all headings, examples, and user/AI interaction text exclusively in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in should be flagged unless the locale constraint is explicitly justified, which is not present here.

Vague Triggers

Low

Confidence: 83% confidence
Finding: This manifest description states the skill supports flight queries, price monitoring, and low-price alerts, but it does not define what user phrases, contexts, or boundaries should activate the skill. In a manifest file, this lack of trigger specificity can contribute to unintended invocation because there are no explicit constraints or negative examples.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: This markdown file contains user-facing natural language content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the policy, forcing a specific language without user choice is a natural-language policy concern.

Static analysis

No suspicious patterns detected.