Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Wordpress AEO Autoblogger

v1.0.0

Autonomous AEO and SEO content generation and optimization engine for scaling business operations. Use when Codex needs to run end-to-end programmatic SEO wo...

0· 36·0 current·0 all-time
byJames Jernigan@how2rank
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (WordPress AEO Autoblogger) align with the code: it generates SEO content, scrapes competitors, builds schema, stores embeddings, and publishes directly to WordPress. The heavy use of LLM providers, search/scraper tiers, ChromaDB, and WP REST API is coherent with the stated purpose.
!
Instruction Scope
SKILL.md instructs the agent to verify a .env with WP_URL, LLM provider keys, and scraper keys and to run setup and the worker scripts. The scripts perform network I/O (scraping multiple tiers, Jina, provider APIs), write to WordPress, and update local DB/vector store. However, the registry metadata declares no required env vars or binaries while the SKILL.md and code expect many secrets and dependencies — an explicit mismatch. The runtime instructions and code also contain an automatic publishing path (direct WP PUT) and analytics operations that will update live posts, which is high-impact and should be highlighted to users.
Install Mechanism
There is no install spec in the registry (instruction-only), but the repository includes requirements.txt listing heavyweight packages (playwright, chromadb, google-generativeai, anthropic, openai, filelock, etc.). Playwright also requires browser runtime components. The lack of an install specification combined with these heavy runtime requirements is a deployment friction / surprise risk but not inherently malicious.
!
Credentials
The code expects many sensitive environment values (e.g., GEMINI_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, GSC_SERVICE_ACCOUNT, SCRAPER_TIER2_KEY, SCRAPER_TIER3_KEY, JINA_API_KEY, PROXY credentials, WP_URL, WP_USERNAME, WP_APP_PASSWORD). Those credentials are proportionate to the declared purpose (publishing + scraping + embedding) — except the registry declares no required env vars, which is an inconsistency. Additionally, config.py hardcodes a CTA_LINK (https://oneclickvids.com) and CTA_TEXT that the pipeline will inject into generated content; that behavior is not called out in the skill description and could be an unwanted promotional/backdoor insertion.
Persistence & Privilege
The skill does not request 'always: true' or other elevated platform privileges. It performs filesystem writes (SQLite DB openclaw.db and ChromaDB under ./chroma_db) and modifies remote WordPress posts via REST API, which are expected for its purpose. No evidence it modifies other skills' configs or requests permanent platform-level presence.
What to consider before installing
This skill implements an autonomous WordPress autoblogging pipeline that scrapes competitors, calls LLMs, builds embeddings, and directly updates posts. Before installing, consider: - Metadata mismatch: the package metadata declares no required environment variables or install steps, but the code and SKILL.md require many sensitive keys (WP credentials, multiple LLM API keys, scraper and proxy credentials). Treat the skill as requiring several secrets and heavy dependencies. - Live publishing: the pipeline will PUT content to your WordPress site using WP_USERNAME and WP_APP_PASSWORD. Use a low-privilege WordPress account (not a site admin) and test on a staging site first. - Hidden promotional CTA: config.py sets CTA_LINK = "https://oneclickvids.com" and CTA_TEXT; the workers will inject CTAs into published content by default. If you don't want that, search and change CTA_LINK/CTA_TEXT before use. - Dependency & environment setup: requirements include Playwright (requires browser installs) and ChromaDB; plan to run in an isolated environment (container/VM) and review setup.py to see how DBs/files are initialized. - Cost and rate controls: the code enforces a daily cost cap but will still make network calls; ensure your API keys have appropriate quotas and billing limits. - Review setup.py and any omitted files: the manifest references setup.py and other truncated files; inspect setup.py and any remaining code for hidden endpoints, telemetry, or unexpected uploads before running. If you proceed, run only on a staging WP site with restricted credentials, remove or change the CTA, and audit network endpoints and the DB path to limit surprise data flow.

Like a lobster shell, security has layers — review code before you run it.

AEOvk979fq4zs6js40bbsjwxx3vp1h84txv3SEOvk979fq4zs6js40bbsjwxx3vp1h84txv3Web Designvk979fq4zs6js40bbsjwxx3vp1h84txv3Wordpressvk979fq4zs6js40bbsjwxx3vp1h84txv3answer engine optimizationvk979fq4zs6js40bbsjwxx3vp1h84txv3google rankingvk979fq4zs6js40bbsjwxx3vp1h84txv3latestvk979fq4zs6js40bbsjwxx3vp1h84txv3rank trackingvk979fq4zs6js40bbsjwxx3vp1h84txv3search engine optimizationvk979fq4zs6js40bbsjwxx3vp1h84txv3

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments