Security audit

Travel Anxiety Management Framework

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to provide travel-anxiety planning templates and its code only returns local JSON, with no evidence of hidden access or harmful behavior.

Reasonable to install if you want structured travel-anxiety planning help. Treat its mental-health and destination suggestions as general planning support, not medical advice or real-time travel information; verify emergency numbers, payments, maps, and local requirements from official or current sources.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (6)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The activation guidance includes generic terms like "anxiety," "management," and "coping if applicable" without clearly defining boundaries or exclusions. These phrases overlap with common conversation and do not specify when the skill should or should not be used, increasing the risk of accidental triggering outside the intended travel-anxiety context.

Vague Triggers

Low

Confidence: 83% confidence
Finding: Several example prompts are broad templates rather than tightly bounded invocations, and one is malformed enough to blur the intended scope (for example, "I'm traveling to anxiety destination"). Without clearer constraints or exclusion examples, these prompts may reinforce ambiguous activation behavior.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The manifest sets `language: en`, and the requirements state "English documentation primary," while the skill also includes a Chinese scenario. This suggests a default language policy without explicit user opt-in or a stated multilingual choice mechanism, which can conflict with language/locale policy expectations.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The Chinese scenario's expected output prescribes specific China-oriented tools and payment methods, such as Alipay and WeChat, as part of the recommended response. This introduces locale-specific assumptions and service preferences without stating that they depend on the user's preferences, region, or consent.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: The manifest sets "language": "en", which indicates a fixed language/locale choice. Under the policy, locale constraints should either offer user opt-in/choice or be clearly documented as justified for a region-specific skill, neither of which is present here.

Static analysis

No suspicious patterns detected.