Security audit

Weather

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward weather helper that sends requested locations to public weather APIs, with no hidden persistence, credential access, or local mutation behavior.

Installers should be comfortable with the agent making network requests to wttr.in or Open-Meteo when weather is requested. Avoid querying highly sensitive precise locations if that privacy boundary matters, and consider using explicit HTTPS URLs for wttr.in examples.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

External Transmission

Medium

Category: Data Exfiltration
Confidence: 89% confidence
Finding: The skill includes a direct HTTPS request to an external third-party API, which causes user-supplied query data such as coordinates or location information to leave the local environment. In context this is core functionality rather than covert exfiltration, but it still creates a real data exposure boundary that should be disclosed and minimized.
Content: Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.
Free, no key, good for programmatic use:

bash
curl -s "https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12&current_weather=true"

Find coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger list contains very broad single-word activations such as "weather" and the Chinese equivalents for weather-related terms. In agent platforms, overly generic triggers can cause unintended invocation during ordinary conversation, leading to prompt hijacking of routing, user confusion, or unnecessary external requests even when the user did not explicitly intend to use this skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill instructs users to send location queries to third-party weather services but does not clearly warn that user-supplied locations and related metadata will be transmitted over the network. While expected for a weather skill, this omission can mislead users about privacy implications, especially if precise locations, airport codes, or other sensitive destinations are queried.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The natural-language content is limited to Chinese and English terms, and the file does not indicate whether users can choose other languages or whether this locale limitation is intentional. Under the language/locale policy, restricting interaction languages without opt-in or justification can be a policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.