Ce skill est 0% plus risque que la moyenne de la categorie Git.
Connectez-vous pour afficher le score detaille du skill.
Recommandations
🌐 Outbound network calls — verify the URLs being contacted.
$npx agentfend install cmn92mqbj009tu1ip24jl1vsb
Description
>
Trust Score
Mis a jour avant-hier
Analyse le
27 mars 2026, 15:43
network_call
Outbound network call
Line 59
Snippets
- If the user's intent clearly matches one skill → fetch that SKILL.md
- If the intent could match multiple skills → fetch all candidates, pick the best fit
2. **Respect robots.txt.** If `robots.txt` disallows `/skills/` or `/agents/`, do NOT fetch skill files from those paths.
3. **Cache within session.** Fetch `skills.txt`/`agents.txt` once per site per session. Don't re-fetch on every interaction with the same site.
4. **Don't over-fetch.** Only fetch the SKILL.md files you actually need. Don't download every skill "just in case."
Connectez-vous pour consulter l'analyse detaillee des risques.
