backlink-guard
Evaluate Backlinks and Track Listing Quality
Poor backlink sources can waste outreach time and create link-spam risks. This skill guides evidence-based research, source vetting, and ongoing verification through the backlink-guard CLI.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "backlink-guard" from https://skillstore.io/skills/zhuyansen-backlink-guard.md and its manifest at https://skillstore.io/api/skills/zhuyansen-backlink-guard/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "backlink-guard". Illustrative request: review a directory without paid credentials.
Expected outcome:
- Source review: available page evidence is summarized separately from audience and backlink metrics.
- Missing signals: traffic, rating, and spam scores require optional providers.
- Next step: review the evidence before deciding whether to submit. No submission was sent.
Using "backlink-guard". Illustrative request: verify a listing containing a sponsored link.
Expected outcome:
- Link verdict: qualified link with a sponsored attribute.
- Placement: report the observed page section alongside the link evidence.
- Next step: compare the observed link with the agreed placement. Ranking credit is not guaranteed.
Using "backlink-guard". Illustrative request: review an audit that found a dead linked page.
Expected outcome:
- Finding: a linked page returned 404. Present its referring-domain count from the tool.
- Recommendation: review the suggested replacement for topic fit before approving a permanent redirect.
- No redirect was changed. Blocked or unreachable pages are reported separately.
Security Audit
SafeMost static alerts match Markdown formatting, documented optional credentials, ordinary local state, and sample URLs rather than malicious behavior. The setup genuinely installs and executes an external PyPI package, whose implementation is absent from the reviewed file. No evidence found of credential theft, obfuscation, or prompt injection; the instructions require approval for paid runs and submissions.
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
โ๏ธ External commands (50)
๐ Network access (6)
๐ Filesystem access (2)
๐ Env variables (4)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/zhuyansen-backlink-guard/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/zhuyansen-backlink-guard?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/zhuyansen-backlink-guard?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhuyansen-backlink-guard/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/zhuyansen-backlink-guard.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
zhuyansen. (2026). backlink-guard security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhuyansen-backlink-guard/audits/4BibTeX citation
@techreport{zhuyansen-zhuyansen-backlink-guard-2026,
author = {zhuyansen},
title = {backlink-guard security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/zhuyansen-backlink-guard/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "backlink-guard security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "zhuyansen"
date-released: "2026-10-31"
url: "https://skillstore.io/skills/zhuyansen-backlink-guard/audits/4"
identifiers:
- type: other
value: "skillstore:zhuyansen-backlink-guard:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Choose relevant launch directories
Review candidate directories for audience, topic fit, and link-spam signals before approving individual submissions.
Review existing backlink quality
Summarize anchor patterns, unusual growth, shared-owner networks, and dead linked pages with evidence and limited next steps.
Research AI citation gaps
Compare cited sources and assistant search visibility for selected buyer questions after approving provider costs.
Try These Prompts
Check [directory domain] for [my domain] using available free signals. Report missing checks and evidence. Do not submit anything.
Verify [listing URL] links to [my domain]. Report link attributes, placement, and unreadable content. Ask before changing the submission log.
Compare [my domain] with [competitor domains]. Quote estimated costs and wait for approval. Prioritize shared sources and report budget omissions.
Prepare buyer questions for [product]. Let me select them, then quote paid costs and wait. Compare citations, mentions, and search ranks after approval.
Best Practices
- Review and isolate the pinned external package before running it with minimal credentials.
- Approve estimated costs before paid runs and approve each submission with its exact destination and text.
- Keep submission logs current and distinguish observed evidence, missing checks, and estimates.
Avoid
- Treating a favorable source grade as permission to send submissions or purchase followed links.
- Creating links in bulk or ignoring a destination list's contribution rules.
- Treating traffic estimates, citation samples, or spam flags as proof of penalties or guaranteed ranking gains.