Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` - Complete documentation (this file)
Security audit
Travel Skill Transfer Planner
Security checks for vulnerabilities and agentic risk
Overview
This is a simple travel-planning skill that generates descriptive JSON advice and does not show hidden network, credential, persistence, or destructive behavior.
This skill appears safe for ordinary use as an informational travel-planning helper. Users should still verify destinations, providers, costs, safety, and cultural guidance with official or current sources because the skill explicitly does not use real-time data or make bookings.
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
- 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 (7)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The manifest declares
language: en, and later the documentation says "English documentation primary," while the skill also includes a Chinese-language scenario. This creates a language/locale constraint in the natural-language specification without clearly offering users a language choice or explaining why English is required.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The trigger keywords are broad and repetitive, including generic terms like 'skill', 'transfer', 'growth', and 'development considerations' that could match many unrelated user requests. Overbroad invocation logic can cause unintended activation, routing user data to the wrong skill, and confusing or unsafe downstream behavior when users receive irrelevant planning advice.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The example prompts use vague constructions like 'help me with' or 'provide framework' that are not unique to this skill and may overlap heavily with general travel, education, or planning skills. In a multi-skill agent environment, ambiguous prompts increase the chance of incorrect dispatch, which can expose unnecessary user context to the wrong component and degrade safety controls based on precise skill selection.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill description presents one example entirely in Chinese and others in English, but it does not explain how the skill chooses output language or whether the user can select a preferred language. That can create a locale-policy issue if the skill implicitly forces a language based on example patterns rather than explicit user choice.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The manifest sets the skill language to "en", which imposes a specific language/locale choice in natural-language configuration. The file does not indicate that users can opt into another language or that the English-only restriction is justified by a region-specific requirement.
- Content
Static analysis
No suspicious patterns detected.