Signalgrid Push

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  1.0.35

Overview

This is a straightforward Signalgrid push-notification skill, but notification text is sent to Signalgrid and also printed to local logs.

Install this only if you want OpenClaw to send notification text through Signalgrid. Use a dedicated Signalgrid key, avoid secrets or sensitive incident details in titles and bodies, and be aware that this version prints notification arguments to local logs before sending.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: The script logs both raw process arguments and the parsed argument object, which can expose sensitive notification contents such as titles, bodies, identifiers, or operational context to stdout, logs, and calling systems. In an agent/automation environment, stdout is often centrally collected or visible to other components, making this a real confidentiality issue unrelated to the skill's core purpose.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The README explicitly instructs users to send notifications through Signalgrid, an external service, but does not warn that notification content, alert metadata, and possibly operational details will be transmitted to a third party. In a notification skill, users may include sensitive system status, incident details, or personal content in alerts, so the lack of disclosure can lead to unintended data exposure and poor security decisions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrases are broad and overlap with common user intents such as 'notify me', 'send a notification', and 'alert me'. This can cause the skill to be invoked unexpectedly, leading users or agents to send message contents to the external Signalgrid service when they may not have intended to use this integration.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill description and usage guidance do not clearly warn that notification title/body content is transmitted to an external third-party service. Without that disclosure, users may include sensitive operational or personal data in notifications, creating an avoidable confidentiality risk.

Missing User Warnings

Medium

• Confidence: 99% confidence
• Finding: This finding is valid because the code prints unredacted CLI inputs and parsed values with no warning or minimization. Since notification payloads often contain sensitive operational or personal data, these debug statements can leak information into shell history proxies, agent logs, CI logs, or other observability systems.

VirusTotal

64/64 vendors flagged this skill as clean.