What is guizang-social-card-skill?
πͺ§ Claude Code / Codex skill β generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial Γ Swiss visual systems, 28 layouts, 10 themes, single-file HTML β PNG. ε°ηΊ’δΉ¦εΎζ + ε ¬δΌε·ε°ι’ε―Ή
Data-security signals
Public, checkable facts about guizang-social-card-skill β they show the risk surface, not what it does with your data at runtime.
- βOpen-source β the AGPL-3.0-licensed code is publicly auditable on its public repository.
- β²High access surface β as an AI agent, it can run with your keys, files, environment and network.
- β’Maintenance β actively published.
- ?Independent exfiltration test β not yet independently tested by Oxavion.
Is guizang-social-card-skill safe? The honest answer.
The signals above show what guizang-social-card-skill can reach. But no public metadata reveals what it actually does with your data once it runs β that only shows up when you watch it in a sandbox. Oxavion runs guizang-social-card-skill with planted canary secrets and watches every outbound channel, then emails you the evidence.
We scan guizang-social-card-skill in our sandbox and email your report. No install, no access to your systems.
How to tell if guizang-social-card-skill is safe
Before you trust any AI tool with your environment, check:
- Is the source auditable? Yes β open-source, you can read it.
- Does it need your keys or credentials? Most agents do β so it holds them at runtime.
- Does it make outbound network calls, and where to? The repo hints at this; only a run confirms it.
- Has it been tested for data exfiltration? Not yet β this is the one you cannot verify from the outside.
The first three you can check from the repo yourself. The last β what it does with your data at runtime β needs a test. That is exactly what an Oxavion scan does β
Frequently asked
- Is guizang-social-card-skill safe to use?
- It depends on what it does with your data at runtime β something a static look can't settle. Oxavion answers it empirically: we sandbox guizang-social-card-skill, feed it canary secrets and data, and report exactly what (if anything) leaves. Request a free scan for a verdict on the version you run.
- How does Oxavion test it?
- An isolated gVisor micro-VM, a transparent egress gateway that captures HTTP/S, DNS and raw TCP, planted canary secrets/PII, and encoding-aware detection β aligned to OWASP LLM Top 10 and MITRE ATLAS, calibrated to zero false-negatives / zero false-positives.