Security audit

sunsetbot-watch

Security checks for vulnerabilities and agentic risk

Overview

This skill only automates a sunset forecast lookup on sunsetbot.top and does not include local code, persistence, credential access, or unrelated behavior.

Before installing, understand that city and date inputs will be submitted to sunsetbot.top through browser automation. This is expected for the skill's purpose; avoid using it for sensitive location queries if that disclosure is a concern.

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
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 (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly uses agent-browser to access an external website, but the skill description does not warn users that their query will trigger third-party web access. This can surprise users, expose query data such as city/date selections to an external service, and reduce informed consent around network activity.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.