Seo Content Writer
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent instruction-only SEO writing skill, with the main things to notice being optional SEO/Search Console data use and saving reusable summaries to memory.
This skill appears safe to use for SEO drafting. Before installing, be aware that it may use connected SEO/Search Console data and may save summaries into memory if confirmed; review those outputs if the content involves private client strategy, analytics, or unpublished business information.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
65/65 vendors flagged this skill as clean.
Risk analysis
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.
Content strategy decisions, drafts, or unresolved issues may persist across sessions and affect later work.
The skill explicitly writes reusable conclusions and open loops into persistent memory paths, which can influence future agent work.
Promotes: approved angles, messaging choices, missing evidence, and publish blockers to `memory/hot-cache.md` and `memory/open-loops.md`
Review memory entries before saving, avoid storing confidential client or business details unless intended, and periodically clean stale content notes.
If these connectors are available, the agent may rely on private website performance or keyword data when drafting content.
The skill may use connected SEO or Search Console integrations, which can expose account- or site-specific analytics data. This is expected for SEO content work, and the artifacts do not show credential capture or unrelated account use.
Use `~~SEO tool` and `~~search console` when connected; otherwise ask for keywords, intent, and competitors.
Connect only the intended SEO/Search Console accounts and review any private data included in generated drafts.
The agent could be influenced by off-package documentation if it chooses to retrieve those links.
The skill points to external GitHub-hosted reference documents that are not included in the reviewed manifest; if fetched at runtime, those external instructions may change outside this artifact review.
Reads: ... prior decisions from [CLAUDE.md](https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/CLAUDE.md) and the shared [State Model](https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/references/state-model.md) when available.
Prefer the packaged reference files when possible, and verify external repository references before relying on them for important workflows.