student-rooms

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill matches a student-housing monitoring purpose, but it relies on an unreviewed external CLI and can start background monitoring, OpenClaw agent alerts, and cron jobs without clear stop or cleanup controls.

Before installing or using this skill, verify the actual student-rooms CLI code because it is not included here. Do not let the agent start watch mode, create cron jobs, or trigger OpenClaw agent sessions unless you explicitly want ongoing automation and know how to stop and remove it. Use trusted notification endpoints and protect any Telegram bot token you configure.

Findings (7)

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.

What this means

The agent may depend on local code that was not reviewed as part of this skill package.

Why it was flagged

The skill instructs use of a local CLI and virtual environment, but the evaluated package contains only SKILL.md and no install spec or code for that CLI.

Skill content
cd /path/to/student-rooms-cli
source .venv/bin/activate
Recommendation

Only use this with a CLI installation you trust, and verify the local repository or package before letting an agent run its commands.

What this means

A monitoring process could continue running and sending alerts after the immediate conversation unless the user knows how to stop it.

Why it was flagged

The skill explicitly encourages a long-running background process, but does not document how the user approves, stops, supervises, or cleans it up.

Skill content
Use `watch` as a background process for ongoing monitoring.
Recommendation

Require explicit user confirmation before starting watch mode, run it only in a visible/supervised session, and document stop and cleanup steps.

What this means

The skill could create scheduled follow-up automation that acts later outside the user’s immediate view.

Why it was flagged

Cron-job creation is persistent scheduled behavior, and the artifact does not define what the job runs, where it is installed, how long it remains, or how to remove it.

Skill content
Optional: `create_job_on_match: true` creates a one-shot cron job for reservation assistance.
Recommendation

Do not enable cron-job creation unless the exact job command, schedule, permissions, and removal procedure are shown to and approved by the user.

What this means

Room-availability details and configured alert context may be shared with another agent session.

Why it was flagged

The skill can pass alert context into another OpenClaw agent session; this is purpose-aligned for alerts but is an inter-agent data flow users should notice.

Skill content
**agent**: Triggers an OpenClaw agent session with the alert as context.
Recommendation

Use the simpler message notification mode unless an agent follow-up is needed, and confirm what context will be passed to the new session.

What this means

Accommodation alerts may be delivered to third-party services or chat destinations configured by the user.

Why it was flagged

The skill supports sending notifications to external webhook and Telegram destinations, which is expected for alerts but sends data outside the local agent environment.

Skill content
| `webhook` | `notifications.webhook.url` | Any HTTP endpoint (Discord, Slack, ntfy.sh) |
| `telegram` | `notifications.telegram.bot_token` + `chat_id` | Telegram bot |
Recommendation

Use trusted notification endpoints and avoid including unnecessary personal details in alert messages.

What this means

Local state may remain after scans and could affect future monitoring results.

Why it was flagged

The skill stores local state about previously seen accommodation options; this is proportionate for deduplication, but the artifact does not specify the storage path or retention.

Skill content
Alerts only on **new** options not previously seen. Persists seen options locally to avoid duplicate alerts.
Recommendation

Document where seen-option state is stored and provide a clear reset or cleanup command.

What this means

If configured, the agent will need access to a Telegram bot credential to send alerts.

Why it was flagged

Telegram notification support requires a bot token; this is expected for the integration, and the artifact does not show hardcoding or leakage.

Skill content
`notifications.telegram.bot_token` + `chat_id`
Recommendation

Store notification credentials securely and use a dedicated bot token with the minimum access needed.