Back to skill

Security audit

Yandex Weather Smarthome

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Yandex Weather helper that sends configured coordinates to Yandex to fetch weather, with no hidden persistence or unrelated access found.

Install only if you are comfortable storing your Yandex Weather API key and home coordinates in environment variables and sending those coordinates to Yandex when weather requests trigger the skill. Expect Russian output by default.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill mandates Russian output regardless of the user's language, even though the trigger examples include both Russian and English. This can override user intent and cause unsafe or misleading responses if the user cannot understand the result, especially when the skill auto-activates.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.

md
1. Open Yandex Weather SmartHome page and go to personal cabinet registration.
2. Register with phone number and accept the user agreement.
3. After registration, copy API key from the personal cabinet.
4. Export the key as `YANDEX_WEATHER_KEY`.

Official page with FAQ and onboarding:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares it requires environment variables and uses an external weather API, but it does not define an explicit tool/permission scope. That omission can allow broader-than-necessary execution in agent frameworks and makes review/enforcement of network and secret access weaker.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The aliases include very generic terms like "weather", "погода", and "forecast", which can cause unintended activation in unrelated conversations. Misfiring a networked skill tied to home coordinates can unnecessarily disclose location-derived information or trigger external requests without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation rules use topic-based conditions such as temperature, wind, and forecast without defining when the skill should not run. In an agent environment, that ambiguity increases accidental invocation and can lead to unnecessary access to environment-backed home coordinates and external API calls.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
import argparse
from urllib import request, parse, error

API_URL = "https://api.weather.yandex.ru/v2/forecast"

CONDITION_RU = {
    "clear": "ясно",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · weather.py (reported line 7)May include surrounding context.

python
import argparse
from urllib import request, parse, error

API_URL = "https://api.weather.yandex.ru/v2/forecast"

CONDITION_RU = {
    "clear": "ясно",

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The request forces the weather API locale to ru_RU, and the script also renders condition labels and user-facing output in Russian. This is a natural-language locale constraint without any visible user opt-in or documented choice mechanism, which fits the policy-violation category for forced language/locale.

Content

No source excerpt is available for this finding.