Hourly Knowledge
Analysis
The skill matches its stated purpose of sending hourly knowledge snippets, with the main things to notice being scheduled messages, small persistent topic history, and account/chat routing metadata.
Findings (4)
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.
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.
每小时整点触发时，为用户推送一条有趣的小知识...通过 cron announce 机制自动推送
The skill is explicitly designed for recurring autonomous push behavior; this is disclosed and central to its purpose, but users should expect scheduled messages.
Source: unknown Homepage: none
The registry metadata provides limited provenance. There is no remote install step or external dependency shown, so this is a provenance note rather than a behavior concern.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
通过 inbound meta 自动获取当前用户的 chat_id 和 channel...从 `config.json` 读取 accountId
The skill uses chat routing identifiers and an accountId to deliver pushes. This is expected for the feature and no token or credential leakage is shown.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
HISTORY_FILE = Path("/root/.openclaw/workspace/memory/hourly-knowledge-history.json")
MAX_HISTORY = 10The helper persists recent topics in a fixed workspace memory file. The retention is bounded to 10 topics, but the file path is global and not clearly separated per user.