Ai Trend Curation

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is mostly aligned with AI trend curation, but it depends on a missing helper script and can post agent-generated Slack messages without clear approval or channel limits.

Before installing, verify the missing `scripts/ai_trends.js` from a trusted source, install `xurl` safely, and configure the skill so Slack posts are previewed and explicitly approved for a known channel.

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.

Concern

ASI04: Agentic Supply Chain Vulnerabilities

What this means

The skill may fail, or it may require adding/running code that was not included in this review.

Why it was flagged

The skill depends on a helper script and instructs Node execution, but the supplied artifact set contains only SKILL.md and no reviewed `scripts/ai_trends.js` file.

Skill content

"requires": { "bins": ["xurl"], "scripts": ["scripts/ai_trends.js"] } ... node scripts/ai_trends.js search

Recommendation

Ship the referenced script with the skill, document its source, and pin or document any dependencies before allowing the agent to execute it.

Concern

ASI02: Tool Misuse and Exploitation

What this means

The agent could post inaccurate, unwanted, or poorly scoped messages into a Slack workspace.

Why it was flagged

The agent selects and formats content, then the workflow posts it to Slack, but the instructions do not require a preview, approval, channel restriction, or rollback step.

Skill content

Step 2: エージェントが以下を判断 ... Step 5: `openclaw message send` で親メッセージ + スレッド返信を投稿。

Recommendation

Require an explicit user review and confirmation step before sending, and make the target Slack channel or audience explicit.

Note

ASI03: Identity and Privilege Abuse

What this means

Installing or invoking the skill may let the agent speak in Slack using an available workspace identity.

Why it was flagged

Posting to Slack uses whatever workspace messaging authority is available to the agent or OpenClaw, even though no explicit credential, channel, or scope is declared in the artifacts.

Skill content

Slack 投稿

`openclaw message send` で親メッセージ + スレッド返信を投稿。

Recommendation

Use least-privilege Slack permissions and restrict the skill to an intended channel or require user confirmation for each post.