AI Daily News

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill mostly matches its AI-news purpose, but it should be reviewed because it can install a package at runtime and includes a shell-based browser helper with unclear input limits.

Before installing, review or disable the automatic yt-dlp pip install and the agent-browser shell helper, then configure only a dedicated Feishu webhook. Expect the skill to make external web requests, write local logs/data, and post reports automatically if you enable the scheduler.

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.

Concern

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Running the news collector can modify the Python environment and execute newly downloaded package code without a separate user approval moment.

Why it was flagged

If yt-dlp is missing, the script installs it from PyPI during collection rather than failing and asking the user to run a reviewed setup step.

Skill content

except ImportError:
    logger.warning("yt-dlp 未安装，尝试使用pip安装...")
    subprocess.check_call(['pip', 'install', '-q', 'yt-dlp'])

Recommendation

Move yt-dlp into the documented requirements, pin the version, and fail with a clear setup instruction instead of installing packages automatically at runtime.

Concern

ASI05: Unexpected Code Execution

What this means

A crafted URL or extractor rule could potentially cause unintended local shell or browser execution when the fallback helper is used.

Why it was flagged

The helper builds shell commands from browser actions, URLs, and optional JavaScript extractor text. If used with configurable or untrusted values, this can escape the intended browser-scraping boundary.

Skill content

full_cmd = f"agent-browser {command}"
result = subprocess.run(full_cmd, shell=True, ...)
run_agent_browser_command(f'open "{url}"', timeout=15)
run_agent_browser_command(f'eval "{js_code}"', timeout=10)

Recommendation

Avoid shell=True, pass arguments as a list, validate or escape URLs, and restrict or remove the generic eval-based extraction path.

Note

ASI03: Identity and Privilege Abuse

What this means

Anyone with the webhook may be able to post to the associated Feishu chat, and the skill will send generated news reports there.

Why it was flagged

The skill uses a Feishu webhook/chat configuration to post reports, which is expected for its purpose but is still an account/workspace posting capability.

Skill content

"feishu": { "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/xxx", "chat_id": "oc_xxx" }

Recommendation

Use a dedicated low-privilege Feishu bot/webhook, keep the webhook secret, and verify the destination chat before enabling scheduled pushes.

Note

ASI10: Rogue Agents

What this means

If scheduled, the skill can continue collecting and posting daily until the scheduler or task entries are stopped.

Why it was flagged

The install guide documents recurring scheduled execution for collection and posting. This is disclosed and purpose-aligned, but it creates ongoing automated behavior.

Skill content

schtasks /create /tn "AI-News-Collect" /tr "python scripts/collect_ai_news.py" /sc daily /st 06:00
schtasks /create /tn "AI-News-Push" /tr "python scripts/push_to_feishu.py" /sc daily /st 08:00

Recommendation

Only enable scheduling intentionally, monitor the first few runs, and know how to stop the scheduler or remove the scheduled tasks.