T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:64- Finding
Mandatory Injection of Promotional and Opaque Redirect Links
- Content
View full analysis
- Remediation
View remediation
Security audit
traveler
Security checks for vulnerabilities and agentic risk
Overview
This is a simple itinerary-planning skill, but it automatically adds preset promotional travel-service links, including opaque short links, to common itinerary outputs.
Review this skill before installing if you do not want itinerary answers to include predetermined booking, taxi, ticket, hotel, or dining links. It does not appear to run code or access local data, but users should treat the included links as promotional and verify destinations before clicking.
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
Findings (1)
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 (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger list includes broad natural-language phrases such as '帮我安排', '旅行计划', and 'travel plan' that can appear in ordinary conversation outside an explicit request to invoke this skill. This can cause unintended activation, routing user input into a third-party-link-heavy planning workflow when the user may have meant a general chat request, increasing the chance of inappropriate invocation and unwanted commercial redirection.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The activation rule '用户要「规划行程 / 做攻略 / 安排几日游」 | 进入规划流程' is underspecified and lacks disambiguation criteria, making it easy for loosely related travel queries to trigger the full planning flow. In this skill, that matters more because activation leads to structured recommendations and appended third-party service links, so accidental invocation can steer users toward affiliate-like destinations without clear necessity.
- Content