Back to skill

Security audit

Whale Weather 🐳

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward weather lookup tool that sends city queries to Open-Meteo and does not show hidden persistence, credential access, or destructive behavior.

Install this only if you are comfortable with queried city names being sent over HTTPS to Open-Meteo for geocoding and weather results. The skill appears limited to weather lookup and comparison, with no evidence of hidden persistence or credential use.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill documentation describes shell scripts that perform live weather lookups using a network data source, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates an authorization and transparency gap: an agent may invoke network-capable code without explicit policy declaration, making review, sandboxing, and least-privilege enforcement weaker.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script sets LANG="zh" as the default, so weather output will be requested in Chinese unless the caller explicitly overrides it. This is a natural-language policy concern because it imposes a specific language by default rather than offering a neutral default or explicit user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script sets LANG_HINT to "zh" when the user does not provide a language, which forces a specific locale by default. The policy allows locale constraints only when the user is given a choice or the restriction is clearly documented and justified; neither is present in this file.

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 · scripts/get_weather.sh (reported line 92)May include surrounding context.

sh
def get_weather_data(lat, lon, tz):
    # Use HTTPS only for transport security
    url = f"https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lon}&current=temperature_2m,apparent_temperature,relative_humidity_2m,wind_speed_10m,weather_code&daily=temperature_2m_max,temperature_2m_min,precipitation_probability_max&timezone={tz}"
    try:
        return fetch_json(url)
    except:

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code sends the user-provided city name and derived location query to external services via HTTPS, but the script does not display any warning, confirmation, or user-facing notice that network calls will occur. For code files, outbound transmission of user data should have some visible disclosure unless clearly communicated elsewhere; this file contains only internal comments, which do not inform the user.

Content

No source excerpt is available for this finding.