Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a cloud video-analysis wrapper for sensitive sleep data, but it silently creates or reuses identities, logs into a remote service, and stores account tokens locally with incomplete user disclosure.
Review before installing. This skill sends sleep-related images or videos to LifeEmergence cloud services, can query cloud history, silently creates or reuses an internal identity, may register/login remotely, and stores tokens in a workspace database. Install only if that account linkage and cloud processing are acceptable for the user’s privacy expectations.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
The skill reportedly performs external API communication, authentication/token handling, automatic user creation/login, and local workspace file operations beyond what the sleep-analysis description suggests. These hidden account and storage behaviors create substantial privacy and trust risks, especially when users may submit sensitive bedroom video or health-related content.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
---
name: "sleep-quality-analysis"
description: "Identifies sleep stages including falling asleep, light sleep, deep sleep, and REM; monitors body movement, nighttime awakenings, and sleep apnea, suitable for sleep monitoring scenarios. | 睡眠质量分析技能，识别入睡、浅睡、深睡、快速眼动阶段，监测体动、夜间觉醒、睡眠呼吸暂停，适用于睡眠监测场景"
version: "1.0.19"
license: "MIT-0"
---
# 😴 Sleep Quality Analysis Skill | 睡眠质量分析技能
> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询
---
## 🧭 技能概览 | Ov
The documented APIs and scenario code are for pet health analysis, which materially conflicts with a skill advertised for sleep-quality analysis. This kind of domain mismatch can cause an agent or operator to invoke the wrong backend, exposing unrelated sensitive health data or producing unsafe, misleading outputs under false pretenses. The mismatch is more dangerous in this context because both domains involve sensitive biometric/health information, increasing the risk of privacy violations and incorrect data handling.
The manifest describes a specialized sleep monitoring skill that identifies sleep stages, body movement, awakenings, and sleep apnea. In this file, the core operation accepts either a local or remote video, uploads it to a generic analysis API, and returns whatever structured report the backend provides, with no code indicating sleep-specific processing, validation, or domain constraints.
The implementation does not match the declared sleep-quality purpose and instead exposes a generic video analysis and history-listing workflow. This kind of capability mismatch is dangerous because it can mislead users, reviewers, and policy controls into granting access to media-analysis features under a benign health-monitoring label, increasing the risk of unauthorized data processing or surveillance-related use.
The user-facing strings explicitly describe a video analysis tool, contradicting the manifest's sleep-monitoring description. This inconsistency is security-relevant because users and automated governance may rely on the manifest for trust decisions while the CLI reveals materially different functionality, enabling deceptive packaging of broader media-processing behavior.
The skill is described as sleep-quality analysis, but this file implements reusable user/account persistence including lookup by username/realname and default-user selection. That scope mismatch is dangerous because it introduces identity and account-handling behavior unrelated to sleep analysis, increasing the chance of covert data collection, over-privileged access patterns, or lateral reuse of personal data across functions.
The User model stores authentication-like tokens (token, open_token) plus personal profile data such as real name, email, birthday, sex, and age, none of which is justified by a sleep-stage analysis skill. In this context, collecting and retaining such data materially increases privacy and credential-exposure risk if the local database is accessed, copied, or reused by other components.
This utility module performs authenticated API calls, token handling, and automatic account provisioning that are unrelated to a sleep-quality analysis skill's declared purpose. In context, this is dangerous because it gives the skill hidden identity and outbound-access capabilities that can transmit user-linked data and create external accounts without clear user consent or strong scope limitation.
The code automatically sends identity data to an external phoneLogin endpoint with silent/register flags, effectively performing login or registration without clear disclosure. In a sleep-analysis skill, this is especially concerning because it creates an undisclosed external account linkage and transmits identifiers unrelated to the advertised local analysis function.
The skill advertises and instructs use of capabilities including shell execution, network access, local file read/write, and environment-variable use, but does not declare any explicit tool scope or allowed-tools boundary. In an agent setting, this weakens least-privilege controls and makes it easier for the skill to trigger broader actions than users would reasonably expect from a sleep-analysis feature.
The manifest frames the skill as sleep analysis, while the documentation extends it to cloud history queries and report-link retrieval. This kind of scope drift is security-relevant because it introduces additional remote data access functions that users and policy engines may not anticipate.
The skill says uploaded attachments are automatically saved as local files without clearly warning about local retention, storage location, or access controls. Because the inputs are sleep-monitoring videos and images, local persistence can expose highly sensitive personal and health-adjacent data.
The skill requires cloud API access for historical report retrieval but does not clearly warn users that their report data is fetched from a remote cloud service. In this context, hidden cloud access is risky because it involves sensitive sleep and possible apnea-related records.
Detected: suspicious.install_untrusted_source