Security audit

时间旅行电视机 📺

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent creative writing skill with no evidence of hidden access, persistence, network use, or destructive behavior.

Install only if you want a Chinese-language immersive history/speculative-fiction helper. Treat outputs as fictional or approximate unless backed by sources, and use care with personal, tragic, or emotionally sensitive scenes.

A.I.G

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

SkillSpector

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 (6)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger list includes very broad, common terms such as "TV", "想看", and "切换", which can cause the skill to activate unintentionally in unrelated conversations. Accidental activation is especially risky here because the skill can generate immersive depictions of sensitive historical, personal, or speculative scenes, increasing the chance of inappropriate or surprising output without explicit user intent.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill invites users to view personal moments (for example, birth scenes) and traumatic historical events in an immersive format, but it does not warn that such depictions may be speculative, privacy-sensitive, or emotionally distressing. In this context, missing safeguards can mislead users into treating generated scenes as factual reconstructions and can expose them to unexpectedly sensitive content.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file presents all headings, labels, and descriptive content in a single language without documenting that the skill is region-specific or that users can choose another language. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This Python file contains user-facing descriptions, prompts, and output strings entirely in Chinese, and the CLI usage/help also assumes Chinese input. Under the natural-language policy rule, forcing a specific language without user opt-in is a policy concern unless the locale restriction is explicitly documented and justified.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: This code file contains user-facing natural-language content in Chinese in the module docstring, and the rest of the emitted interface text is also Chinese. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern unless the locale restriction is explicitly documented and justified.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This markdown file contains only Chinese-language content, beginning with the title at L01 and continuing throughout the file. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or justification can be a locale-policy issue.

Static analysis

No suspicious patterns detected.