UAPI 答案之书 接口

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 12:36 PM UTC
• Version: 1.0.0

Overview

This skill is a narrow wrapper for a public random-answer API, with the main caution being that its generic trigger could call the API unintentionally.

Before installing, consider narrowing activation to '答案之书' or 'answerbook ask' rather than the standalone word 'ask'. The skill appears safe for its purpose, but questions sent to it may be transmitted to the UAPI service, and an optional UAPI key should only be provided deliberately for that service.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger phrase "ask" is extremely generic and likely to match many unrelated user requests, causing this skill to be invoked when the user did not intend to use the Answerbook endpoint. In an agent environment, over-broad routing can lead to incorrect external API calls, confusing behavior, and unintended data exposure to third-party services.

Natural-Language Policy Violations

Medium

• Confidence: 79% confidence
• Finding: The primary title and operational guidance are written in Chinese, and the description begins with Chinese-language instructions without stating that the skill can respond in the user's preferred language. This can amount to an implicit language policy constraint because no opt-in or language choice is documented.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The skill enables implicit invocation via `allow_implicit_invocation: true` without any documented narrow trigger conditions or user-confirmation guardrails. This can cause the agent to call the external UAPI endpoint based on ambiguous user phrasing such as "ask" or loosely related requests, increasing the risk of unintended tool use and unexpected data flow to the API.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger keyword "ask" is excessively generic and is likely to match ordinary user requests that have nothing to do with the Answerbook feature. This can cause accidental skill invocation, leading the agent to route unrelated prompts to this API and produce incorrect behavior or unintended external calls.

Natural-Language Policy Violations

Low

• Confidence: 82% confidence
• Finding: The display name, description, and prompt are written entirely in Chinese, which suggests a fixed language choice in the skill's natural-language interface. The file does not indicate that users can opt into this locale or that the Chinese-only behavior is required for a documented region-specific purpose.

Static analysis

No suspicious patterns detected.