Back to skill

Security audit

tv-launcher-prototype

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk front-end prototyping helper for Smart TV launcher-style interfaces, with no evidence of hidden execution, credential access, persistence, or data exfiltration.

Install this if you want a Chinese-language helper for Smart TV or 10-foot UI prototypes. Be aware it may activate for broad launcher or big-screen interface requests, so review generated files before use and clarify when you do not mean a TV-style prototype.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (5)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger conditions are extremely broad and include generic phrases such as requests to design a launcher or any TV/big-screen interface, which can cause the skill to activate in situations where the user did not intend it. Over-broad invocation increases the chance of capability hijacking, misrouting user requests, and suppressing more appropriate skills or baseline handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill metadata and instructions are written to enforce Chinese-language behavior without indicating that output should follow the user's language preference. This can cause inconsistent user experience, unintended disclosure of assumptions about the user, and operational misuse when the skill is invoked for non-Chinese requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This manifest-style JSON contains Chinese-only prompt and output text, which bakes a specific language/locale into the skill evaluation behavior. The file does not indicate that language choice is optional or that the skill is intentionally region-specific, so it can violate the language/locale policy for natural-language content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

These evaluation strings are also written exclusively in Chinese and expect Chinese-language behavior by default. Because no opt-in or locale-scoping is provided in the file, this is a natural-language policy concern rather than a functional issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The third evaluation case continues the same pattern of Chinese-only prompt and expected-output content. Without a stated regional constraint or user language selection, the file implicitly forces one locale across the skill's natural-language interface.

Content

No source excerpt is available for this finding.