Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Daily Briefing
v1.0.0Generate daily morning briefings with weather, traffic limits, and news. Provides structured data collection scripts for stable, reproducible briefing genera...
⭐ 0· 27·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description align with the code: scripts fetch weather (wttr.in), compute traffic limits, and collect/format news. The included modules (data-collector, news-collector, generate-briefing) implement the declared functionality.
Instruction Scope
SKILL.md directs the agent to run the package's node scripts and to use a 'kimi_search' tool for news. That keeps scope to fetching/formatting data, but the docs/cron examples also reference other skills (an email-sender) and absolute paths (/root/.openclaw/...), which assume environment-specific tooling and cross-skill access.
Install Mechanism
There is no registry install spec (skill is instruction+code only). package.json declares cheerio; package-lock present. No remote downloads or extract operations in the skill itself. However the registry metadata omits an install step — you will likely need to run npm install in the skill directory to satisfy dependencies.
Credentials
The skill requests no env vars or credentials (good). But it executes shell curl commands (child_process.execSync) with interpolated inputs (e.g., city in getWeather and URL/User-Agent in fetchWithCurl). Those constructs can allow command injection if untrusted inputs are passed. Additionally, news-search imports 'kimi-search' but that package is not declared in package.json — it assumes an external platform-provided tool, which is an undeclared dependency.
Persistence & Privilege
always:false and no code attempts to modify other skills or global agent configuration. The skill writes a local .cache directory only. Cron examples are optional and do not force installation.
What to consider before installing
This skill mostly does what it says (weather, traffic rules, scrape/organize news), but review before installing:
- Network access & external fetches: Scripts use curl (via execSync) to fetch wttr.in and multiple news sites. Expect outbound HTTP(S) traffic when running the skill.
- Shell command risk: The code builds shell commands with string interpolation (execSync + curl). If untrusted inputs are passed (for example a crafted city string), that could allow shell injection. Prefer running in a sandbox or only with trusted inputs; consider patching the code to URL-encode inputs or to use a safe HTTP client (undici/fetch) instead of shelling out.
- Undeclared dependency: news-search.mjs imports 'kimi-search' but package.json does not list it. Either the platform must provide this tool, or the module will fail. Confirm the runtime environment supplies kimi_search or add the dependency.
- Path assumptions / cross-skill examples: README/cron examples reference /root/.openclaw and another skill's sendEmail script. Those are examples — they assume other skills and elevated path access. Do not copy these cron/email commands into production without verifying your environment and permissions.
- Mitigations before use: run npm install in a controlled environment, inspect and (if needed) sanitize any inputs passed to the scripts, run the skill in a restricted container or VM, and verify or add the missing kimi-search dependency or adapt news-search to use the included news-collector which already scrapes known sites.
If you want, I can (a) point out exact lines that do shell interpolation, (b) suggest safe code changes to remove shell usage, or (c) prepare a checklist to harden this skill before enabling it in a production agent.scripts/data-collector.mjs:40
Shell command execution detected (child_process).
scripts/news-collector.mjs:33
Shell command execution detected (child_process).
scripts/data-collector.mjs:8
File read combined with network send (possible exfiltration).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk975sb82qv0swgbtv2wg5jma81845178
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
