Back to skill
v0.1.1

Let Me Know

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 5:22 AM.

Analysis

This is mostly a notification helper, but it asks the agent to create background heartbeat jobs and, in one failure case, restart the gateway, which is broader authority than a simple update skill needs.

GuidanceBefore installing, confirm you are comfortable with the agent sending progress messages and possibly creating temporary heartbeat jobs. Do not allow the gateway restart behavior unless you explicitly want this skill to have that operational authority.

Findings (2)

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
只有在必须脱离当前执行流时才用 cron 心跳 ... 通过 `cron add` 创建心跳 job ... 创建后把返回的 **heartbeatJobId** 写入状态文件 ... 在任务**成功/失败的 finally** 里调用 `cron remove <heartbeatJobId>`

The skill can create a scheduled background heartbeat job that persists outside the immediate turn. It does include cleanup and deduplication requirements, so this is purpose-aligned but still worth user attention.

User impactIf cleanup fails, the user could continue receiving heartbeat messages after the original task is over.
RecommendationPrefer the in-turn heartbeat mode, keep the interval reasonable, and verify that any cron heartbeat job is removed after completion or failure.
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
If cron removal fails due to gateway timeout, retry removal; if still stuck, use gateway restart (requires `commands.restart: true`) and retry.

Restarting a gateway is a privileged, high-impact action and is not clearly necessary for a notification-only skill. The instruction does not require explicit user confirmation before using that capability.

User impactA gateway restart could interrupt the agent, other tasks, or other users depending on the environment.
RecommendationRemove the gateway-restart fallback or require explicit user/admin approval before any restart; use bounded cron cleanup and manual escalation instead.