v1.0.0

Google AI Usage Monitor

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 5:26 AM.

Analysis

The skill’s monitoring purpose is coherent, but it relies on a logged-in Google browser profile and recurring Discord alerts, so a user should review account and channel access before installing.

GuidanceReview this skill before installing. It appears intended to do what it says, but you should only run it with the correct Google account, a scoped project, and a private Discord channel. If you enable the cron or heartbeat setup, make sure you know when it will run, what it will report, and how to turn it off.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Rogue Agents

SeverityLowConfidenceHighStatusNote

SKILL.md

"kind": "cron", "expr": "0 20 * * *" ... "message": "检查 Google AI Studio 用量并发送报告到指定 Discord 频道" ... Add to HEARTBEAT.md: "Check usage if last check > 24 hours"

The skill documents a recurring scheduled agent turn and heartbeat reminder, which can keep the monitoring behavior running beyond a single manual invocation.

User impactOnce configured, the agent may repeatedly check usage and send reports on a schedule without a fresh approval each time.

RecommendationEnable the cron or heartbeat setup only after confirming the schedule, target project, destination channel, and how to disable or remove the recurring task.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusConcern

SKILL.md

browser action=open targetUrl="https://aistudio.google.com/usage?project=YOUR_PROJECT_ID&timeRange=last-28-days&tab=rate-limit" profile=openclaw ... Check if logged into correct Google account

This directs the agent to use an existing browser profile and Google login to access project usage data, while the registry metadata lists no required credential.

User impactIf the wrong or overly privileged Google session is active, the agent may view and report quota, usage, tier, and project information for that account.

RecommendationUse a dedicated least-privileged Google account or project, confirm the project ID and browser profile before use, and declare the Google session/profile requirement clearly.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityMediumConfidenceHighStatusNote

SKILL.md

"delivery": { "mode": "announce", "channel": "discord", "to": "CHANNEL_ID" } ... "项目": "{project_name}" ... "付费等级": "{tier}"

The skill sends Google AI usage reports, including project and tier information, to a Discord channel.

User impactProject usage and quota details could be visible to everyone with access to the configured Discord channel.

RecommendationSend alerts only to a private, appropriate channel and avoid including more project or billing-context detail than the recipients need.