Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Fennecseo Audit

skill · berabuddies/SemiaApache-2.0 licenceAudited 19 Oct 2026 · source ad9eea27f661

★ 613pushed 47 days ago
✓SAFEGrade B · 89/100 · 19 Oct 2026 · ad9eea2
613repo stars · whole berabuddies/Semia

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit ad9eea27f661 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Uses Fennec SEO Auditor results to audit a URL. Invoke when user wants a quick on‐page/technical SEO health check or to verify favicon/meta/schema and GEO readiness.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Fennecseo Audit (berabuddies/Semia)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/berabuddies/fennecseo-audit

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha ad9eea27f661 · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherberabuddies GitHub organizationOwner of the repository this skill is read from
  • Source folderberabuddies/Semia/tests/fixtures/skills/2winter-dev/fennecseo-auditThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictad9eea27f661A new audit runs when the source changes
  • Repository statusNot archivedLast push 47 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Uses Fennec SEO Auditor results to audit a URL. Invoke when user wants a quick on‐page/technical SEO health check or to verify favicon/meta/schema and GEO readiness.

---
name: "fennec-seo-audit-en"
description: "Uses Fennec SEO Auditor results to audit a URL. Invoke when user wants a quick on‐page/technical SEO health check or to verify favicon/meta/schema and GEO readiness."
---

# Fennec SEO Audit Skill (with Fennec SEO Auditor Extension)

This Skill is designed to work together with the Chrome extension **Fennec SEO Auditor** to run a quick SEO health check on any given page.

Typical use cases:

- Get a fast overview of a page’s SEO basics (title, meta, headings, canonicals, etc.)
- Verify favicon, Open Graph and structured data exposure
- Spot common technical issues (HTTP status code, redirects, indexability, robots rules)
- Judge whether a page is “GEO‐ready” as a candidate source for RAG / LLM answers

> Chrome extension link:  
> https://chromewebstore.google.com/detail/fennec-seo-auditor/fifppiokpmlgceojhfdjbjjapbephcdo

---

## When to invoke this Skill

Use `fennec-seo-audit-en` when:

- The user provides a URL and asks for a **quick SEO audit / health check**
- The user wants to confirm favicon / meta / Open Graph / structured data are implemented correctly
- A new article / landing page has just been published and needs a basic SEO / GEO review
- The user wants to use a real page as a **GEO example**, to see how well it exposes:
  - indexability signals
  - semantic structure
  - brand / entity signals

Avoid using this Skill as:

- A full‐site crawler or large‐scale technical audit (it’s better suited for spot checks)
- A replacement for log analysis or server‐level diagnostics

---

## Human steps (what the user does with the browser)

1. Install and enable the **Fennec SEO Auditor** Chrome extension  
   Link: `https://chromewebstore.google.com/detail/fennec-seo-auditor/fifppiokpmlgceojhfdjbjjapbephcdo`

2. Open the target page you want to audit  
   (e.g. a blog post, product detail page, homepage, documentation page)

3. Click the **Fennec SEO Auditor** icon in the browser toolbar:
   - Run the standard audit (On‐page / HTML / Links / Images, etc.)
   - Wait for the extension to finish and show the report

4. Share the key parts of the report with the assistant:
   - Either copy key findings as text
   - Or summarize / extract the main issues
   - Screenshots are fine too if the platform supports them

The assistant will then interpret the audit and turn it into a clear action plan.

---

## Assistant responsibilities when this Skill is invoked

When `fennec-seo-audit-en` is triggered, the assistant should:

1. Make sure the user has run Fennec SEO Auditor on the target URL (and guide them if not).

2. Parse and structure the audit output, covering at least:
   - **Page basics**: URL, title, meta description, H1/H2, main intent
   - **Technical layer**: HTTP status, canonical, index directives, robots and sitemap hints
   - **Content & readability**: length, keyword coverage, duplication, thin or low‐value sections
   - **Media & links**: image ALT attributes, internal link structure, external links / broken links
   - **Brand & GEO signals**: favicon, brand / organization info, logo exposure, Schema.org markup

3. Highlight **high‐priority issues** that are likely to affect:
   - indexability and crawling
   - CTR and snippet quality
   - perceived trust / authority

4. Provide concrete, implementable recommendations for each important issue, not just a restatement of the report.

5. Add a **GEO / RAG perspective**, for example:
   - Is the page easy for a retrieval system to index and match semantically?
   - Are there clear entity signals (Organization / Person / Product, etc.) that help LLMs trust this source?
   - Does the page risk being treated as “thin / spammy / boilerplate” content?

---

## Recommended output structure

When responding based on Fennec SEO Auditor results, the assistant should aim for a structure like:

1. **Page overview**
   - URL, title, H1, target intent / query

2. **Issue summary (with priorities)**
   - High / Medium / Low priority list

3. **Detailed findings and fixes**
   - Meta & snippets (title, description, OG tags)
   - Content & headings
   - Internal links & anchors
   - Technical / indexability
   - Media (images, ALT text)
   - Structured data & entity signals

4. **GEO / RAG perspective**
   - How well this page can be retrieved, re‐ranked and cited by LLMs
   - Additional suggestions (e.g. add FAQ schema, clarify sections, add data / sources)

---

## Notes and constraints

- The assistant **does not** directly control the browser or extension; it relies on the user to run Fennec and share the output.
- Recommendations should balance:
  - Classic SEO (crawlability, rankings, CTR, readability)
  - GEO / LLM needs (structured signals, semantic clarity, trustworthy sources, clear entities)
- The assistant should avoid generic advice and tie recommendations back to:
  - the user’s actual page
  - the specific issues reported by Fennec SEO Auditor.

Excerpt, first 4,937 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit ad9eea2

Download folder ↗
git clone https://github.com/berabuddies/Semia
git -C Semia checkout ad9eea27f661

The author documents no install command, so this uses the repository directly. Our verdict covers commit ad9eea27f661 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source ad9eea27f661

Questions about Fennecseo Audit

What does the Fennecseo Audit skill do?
Semia, security audit for AI agent skills.
Is Fennecseo Audit safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Fennecseo Audit access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (ad9eea27f661), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.