Security audit

Xiaomi

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent smart-home control purpose, but it under-discloses sensitive Xiaomi token handling and uses a risky install path.

Review this skill before installing. Treat Xiaomi device tokens like passwords, avoid putting them in repository Markdown files or chat logs, and store them in a dedicated secrets mechanism outside shared project files. Do not rely on the advertised token extractor unless the actual script is supplied and reviewed, and consider pinning the install dependencies before use. Use extra care with commands that control heaters, smart plugs, or cooking appliances.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:4
Finding: Unpinned Third-Party Dependencies Execute with User Privileges
Content: View full analysis
Remediation: View remediation
' ``` 2. Use a locked dependency specification that also constrains transitive dependencies. 3. Require cryptographic hashes for downloaded artifacts where the installation mechanism supports them. 4. Document and restrict installation to a trusted package index. 5. Review the selected package artifacts and their dependency tree before release. 6. Avoid modifying pipx environments through hard-coded paths. Use supported pipx commands, such as dependency injection, with platform-independent environment discovery. 7. Run installation without administrative privileges and in an isolated environment. 8. Establish an update process in which dependency changes receive a new security review before constraints are modified. ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:24
Finding: Xiaomi Device Authentication Tokens Are Directed to Plaintext Markdown Storage
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly promotes a bundled token extractor that pulls device IPs and Xiaomi device tokens from the user's cloud account, but it does not warn that these are sensitive credentials. Those tokens enable direct LAN control of devices, so exposing or mishandling them can lead to unauthorized control of home appliances and disclosure of household device inventory.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill instructs users to store device IPs and tokens in local reference files without warning that these files become a local secret store. If these files are committed to version control, exposed through backups, or read by other local tools, an attacker could gain persistent control over Xiaomi devices on the LAN.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.