UAPI 查询 Steam 用户 接口

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent read-only helper for looking up Steam public profile summaries through UAPI, with a minor routing caution around broad trigger wording.

Install this only if you want your agent to query Steam profile summaries through uapis.cn. Confirm the user request is specifically about a Steam user before invocation, and do not pass a Steam Web API key unless necessary for that request.

SkillSpector

By NVIDIA
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
Confidence
93% confidence
Finding
The trigger keyword "summary" is excessively generic and can match many unrelated user requests, causing the agent to invoke this Steam-specific skill when the user intended something else. In a routing system, overbroad triggers can lead to incorrect tool selection, unintended data lookups, and disclosure of third-party profile information in contexts unrelated to Steam.

Vague Triggers

Low
Confidence
82% confidence
Finding
The invocation guidance says to use the skill when the request "directly corresponds" to querying a Steam user, but it does not define exclusion conditions or boundary cases. This ambiguity increases the chance of accidental misrouting to the endpoint, especially when user requests are only partially related to gaming, profiles, or summaries.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal