Backlink Analyzer
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent instruction-only SEO backlink analysis skill, with noteworthy but disclosed persistence and disavow workflow guidance that should be handled with user approval.
This skill appears safe to use for backlink reporting and planning. Before installing, be aware that it may persist SEO findings into memory files and that any disavow upload to Google Search Console should be manually reviewed and explicitly approved.
Findings (3)
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.
If the agent is given access to Search Console, a mistaken disavow upload could harm the site's SEO performance.
Uploading a disavow file changes a Google Search Console property and can affect search rankings. The artifact warns about impact and includes safeguards, so this is purpose-aligned but should require explicit user authorization.
Unnecessary disavow can hurt rankings. ... | 7 | Upload to Google Search Console | Back up previous file first |
Use the skill for analysis and file preparation, but require an explicit user review and approval before any Search Console upload or account-changing action.
Backlink findings, competitor details, or SEO decisions may persist beyond the immediate conversation.
The skill intentionally persists backlink findings and follow-up items into memory files, meaning analysis results can be reused in later tasks.
**Writes**: a user-facing monitoring deliverable and reusable summary. ... **Promotes**: significant changes, confirmed anomalies, and follow-up actions to `memory/open-loops.md` and `memory/decisions.md`.
Review what is written to memory, avoid storing unnecessary sensitive business context, and clean up memory entries when they are no longer needed.
The agent may rely on external documentation or connector instructions outside the installed artifact set.
The skill references external GitHub documents and connector guidance that are not included in the provided file manifest. They appear documentation-related and purpose-aligned, but they can still influence how the agent performs the workflow.
Reads: current metrics, baselines, alert thresholds, and reporting context from [CLAUDE.md] ... and the shared [State Model] ... when available. ... All integrations optional (see [CONNECTORS.md] ...).
Review referenced connector, security, and state-model documents before relying on them for operational or account-connected workflows.