eeat-content-quality-audit
v1.0.0Systematic content quality audit based on 80 CORE-EEAT standards, evaluating content's GEO (Generative Engine Optimization) and SEO (Search Engine Optimizati...
⭐ 0· 74·0 current·0 all-time
byyaoo-2818@281862066-a11y
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill name and description match the SKILL.md and included reference files: it defines an 80-item CORE-EEAT audit, scoring rules, veto items, and content-type weights. There are no extra environment variables, binaries, or config paths declared that would be unnecessary for a content audit.
Instruction Scope
The runtime instructions are narrowly scoped to requesting content text/URL or file path, running the 80-item scoring procedure (using the included reference docs), and marking site-level items as N/A when not accessible. The SKILL.md explicitly recommends manual input and notes which checks require site-level data, and it does not instruct the agent to read local secrets, arbitrary system files, or contact hidden endpoints.
Install Mechanism
There is no install spec and no code files to be written or executed; this is instruction-only, so nothing will be downloaded or installed during skill use.
Credentials
The skill declares no required environment variables, credentials, or config paths. The audit workflow acknowledges that some Authority/Trust items require site-level data and instructs marking them as N/A when unavailable, which is proportionate.
Persistence & Privilege
The skill is not forced-always (always:false) and does not request persistent or elevated privileges. Autonomous invocation is allowed by default on the platform but poses no additional risk here because the skill has no install or secret requirements.
Assessment
This skill appears coherent and low-risk: it is instruction-only, ships the audit criteria, and requests no secrets or installs. Before using it, avoid pasting sensitive content into the audit prompt (do not include private API keys or PII embedded in content). If you provide a URL, confirm whether your agent will fetch the page itself or you will paste the page text—the SKILL.md recommends manual input and flags site-level checks as N/A when the agent can't access them. Lastly, remember that 'benign' here means the skill's scope is coherent — validate any audit recommendations manually before acting, since judgments about credibility and legal claims still require human review.Like a lobster shell, security has layers — review code before you run it.
latestvk97dbq8sxebynwwnqg1jbqx62983qba6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.