Wjs Publishing Wechat

PendingVirusTotal audit pending.

Overview

No VirusTotal analysis has been recorded yet. File reputation checks will appear here once the artifact hash has been scanned.

Findings (0)

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.

What this means

If that external repository changes or is compromised, the agent may run unreviewed code while handling your article drafts and local authentication.

Why it was flagged

The skill requires installing an external GitHub repository directly into the agent skills directory without a pinned commit, checksum, or reviewed source in this artifact set.

Skill content
必须装好 `gpt-image-2-skill`:

git clone https://github.com/Wangnov/gpt-image-2-skill /tmp/g
cp -r /tmp/g/skills/gpt-image-2-skill ~/.claude/skills/
Recommendation

Review and pin the external dependency before installing, or use a known commit/checksum and avoid copying unreviewed skills into the agent skills directory.

What this means

Local command execution is expected for this workflow, but it means the helper code runs on your machine under your user account.

Why it was flagged

The skill intentionally executes a Node.js wrapper from the external gpt-image-2-skill package to generate images.

Skill content
RESULT=$(node "$WRAPPER" --json --provider codex images generate \
Recommendation

Run the scripts only after verifying the helper dependency and from article folders you trust.

What this means

The skill can use accounts that may incur image-generation cost and can create drafts in the configured WeChat Official Account.

Why it was flagged

The workflow depends on local Codex authentication and WeChat Official Account API credentials.

Skill content
唯一支持:Codex `~/.codex/auth.json` ... `md2wechat` CLI 已安装并配置好 `WECHAT_APPID` + `WECHAT_SECRET`
Recommendation

Use least-privilege credentials where possible, confirm the configured WeChat account, and do not run the upload step until the draft and target account are correct.

What this means

Running the script can place article content and images into your WeChat Official Account drafts, although it does not appear to publicly publish the article by itself.

Why it was flagged

The upload helper uses md2wechat to upload images and create a WeChat draft, which mutates the configured account's draft area.

Skill content
md2wechat upload_image cover.png ... md2wechat create_draft draft.json
Recommendation

Treat upload-draft.sh as an account-changing action; inspect the generated files first and run it only when you intend to create a WeChat draft.

What this means

Private drafts may be sent to the image-generation provider before publication.

Why it was flagged

The illustration generator reads the full article markdown and sends it as instructions to the external Codex-backed image-generation wrapper.

Skill content
article  = open(sys.argv[2]).read() ... --provider codex images generate ... --instructions "$INSTRUCTIONS"
Recommendation

Do not use the automatic image-generation step for confidential drafts unless you are comfortable sending the article content to the configured provider.