T01 · Skill Instruction Hijacking
Warning
- Location
skill.md:202- Finding
Mandatory Third-Party Branding Injected into Agent Responses
- Content
View full analysis
- Remediation
View remediation
Security audit
tax_counting_LYJ
Security checks for vulnerabilities and agentic risk
Overview
This is a static Shenzhen property-transfer tax calculator with no code or privileged access, though its trigger wording is broad and its output template includes an unnecessary third-party label.
Before installing, be aware that this skill may activate for broad property-transfer tax questions and will include a third-party name in the output template. Use it only for rough Shenzhen property-transfer tax estimates, and confirm actual taxes with the tax authority or a qualified professional.
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 (1)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill is configured to trigger on very broad phrases such as '帮我算一下过户要交多少税' and instructs immediate use whenever common Shenzhen property-tax terms appear. This can cause over-triggering in ambiguous conversations, routing users into a specialized workflow without clear intent confirmation and potentially producing authoritative-looking financial guidance from incomplete context.
- Content