Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Write My Blog
v0.1.0Enables the agent to create, manage, and publish a full-featured blog autonomously. The agent can write posts, upload media, switch between 10 premium design...
⭐ 2· 602·2 current·2 all-time
byHarsh Raj@harshraj001
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description (create/manage/publish a blog) align with the included code (Next.js blog, APIs, themes, deploy scripts). However the registry metadata declares no required env vars or binaries while the shipped scripts and platform clearly expect database keys, cache endpoints, and optional CLIs (Vercel/wrangler). That mismatch between declared requirements and actual needs is an inconsistency.
Instruction Scope
SKILL.md tells the agent to run scripts (scripts/setup.sh, deploy scripts) that will install dependencies, write a .env.local file containing API keys/service credentials, run migrations, and potentially deploy to cloud providers. The instructions permit run_command and file operations but do not restrict paths; the setup script in non-interactive mode overwrites .env.local without prompting. Those behaviors broaden the agent's scope to creating and storing sensitive secrets on disk and interacting with external services.
Install Mechanism
There is no formal install spec in the registry (instruction-only), but the provided setup.sh runs 'npm install' which will fetch many public npm packages (package-lock.json included). This is expected for a Next.js app but is a non-trivial install step (network downloads, native optional deps). No obscure download URLs or self-hosted archives were found.
Credentials
The repository and scripts require/consume sensitive credentials (SUPABASE_SERVICE_KEY, MONGODB_URI, REDIS_URL, various DB provider configs) and generate/write an API_KEY into .env.local. Yet the skill metadata lists no required env vars and SKILL.md does not enumerate these upfront. Requesting or writing high-privilege keys (e.g., Supabase service role key) is disproportionate without explicit disclosure. In non-interactive (agent) mode these values must be present in the agent environment or flags, increasing exposure risk.
Persistence & Privilege
The skill does not set always:true and does not modify other skills. It does create/overwrite local configuration (.env.local) and can deploy to external hosts (Vercel/Cloudflare) if run. The non-interactive overwrite behavior and creation of API keys on disk are noteworthy but are normal for deployment scripts.
What to consider before installing
This package appears to be a legitimate self-hosted blog platform, but exercise caution before running its setup or allowing an agent to run it autonomously. Key points to consider:
- The repo and scripts will ask for or expect sensitive credentials (Supabase service role key, MongoDB URIs, Redis URLs) and will write them into platform/.env.local; the skill metadata did not declare these needs. Only provide least-privilege keys, and avoid giving high-privilege service keys unless you understand the implications.
- The setup script can run non-interactively and will overwrite an existing .env.local without prompting in that mode. Don’t run non-interactive setup in an environment where the agent has access to unrelated secrets.
- The setup runs npm install (downloads many packages). Run it in an isolated environment (container/VM) if you want to limit blast radius.
- Review scripts (scripts/setup.sh, deploy-*.sh, and any DB adapter code) yourself before executing. If you plan to deploy, create dedicated deployment/service accounts and rotate keys after use.
- If you want the agent to operate this skill, prefer interactive setup and manual provisioning of cloud credentials rather than exposing them to the agent runtime. If you have questions about specific files or want a focused review of the DB adapters or middleware, ask and I can inspect those parts in detail.Like a lobster shell, security has layers — review code before you run it.
latestvk974sypn6xysnayvkcm9v24r8581bzej
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
